Fetching metadata from the HF Docker repository...
Oct 1 09:38 Withheld-run fixes: recorded margin floor; re-blend bounded by the recorded cap; precise break-even revenue and sign-aware growth clause; pre-revenue message; no retry invitation for deterministic failures Sep 30 08:16 BSX root causes: token-safe segment keywords + parent-sector compatibility gate; growth label; semantic gate before the PM Sep 28 19:15 Fundamentals table: compact headers + provenance footnotes; print-safe tables 18:47 HISTORICAL_QUALITY_LABEL: fail when a stored quality state was not read 18:46 Lineage labels read the frozen state (Mapping, not dict) 18:36 Claim lineage: typed guidance/engine-vs-consensus relations, lineage checks, HistoricalMetricQuality label 18:02 Guidance trigger subject uses the row's own label (keeps scope qualifiers like 'excluding OSTTRA') 17:46 Open items: break-even solved on the adopted margin (floor never cuts); recalibrated thesis gate; benign co-citation; no triggers on price multiples; nominated peers only; benchmark applicability; merged guidance rows; engine-EPS basis; market composite noun; insider transaction counts; filer names; quarter limitation; story revenue/share precision 12:43 Gate calibrated offline (reviewers' standard rubric; extended thinking; bounded retries; run deadline); triggers refuse sources that include a separated business 10:25 Structured arguments items 1-2: thesis rests_on + two-pass gate with report context, one bounded repair turn, typed trigger labels, evidence printed in full once, identifier and authored-once audits, relaxed evidence limits, past returns withheld 06:36 Structured arguments (crucible.args/2): typed evidence + figure-free judgement, templated figures, validated forwarding between rounds, semantic gate; data-quality notes kept out of author prompts Sep 27 21:03 Predicate verb agreement with its subject 20:57 High/low about an assumption is a typed assessment; trigger basis not written twice 20:24 Universal valuation claims checked against every anchor; consistent tokenisation in the doubling check 20:11 Rebuttal topics labelled as the opponent's claim; forecast reader names with direction check; complete ownership breakdowns 20:04 Speech lineage (management statements need their quoted words), verbal magnitude bands, spelled counts, multiples named by metric 19:54 No mid-sentence truncation of authored prose; incomplete-sentence rule; money figures named by concept; named break-even counterparts; count agreement 19:46 Clause-scoped valuation/logic rules, trend mood, parenthesis splitter, issuer as performance subject, hyphen-normalised doubling, count units, PP-modified predicate subjects 19:32 Remaining SPGI items: predicate/list render slots, expected-return direction, value proximity band, metric-family comparisons, trigger guidance basis, composite input labels, segment margin cap disclosure + reconciliation 19:19 Acceptance fixes: ownership others count, relation clause/operand doubling, expectation comparatives, assumption assessments, stock performance claims, quote speaker roles, statement domains 18:43 Descriptive evidence cannot be a reason; failed guidance extraction retried and not reported as absence; clause phrase capitalisation 18:37 R5: PASS/FAIL status tokens are case-sensitive (ordinary 'fail' is not QA vocabulary) 18:31 Evidence lineage: final-claim lineage, public language only, EvidenceUse conclusion types, NewsEvidenceClaim, qualifier and basis ownership, full guidance table 18:04 Title-case strong ratings checked; seats with no publishable prose say so 17:59 Deterministic fallbacks for empty summary/PM sections; relation tokens shown as clauses in PM anchors 17:45 Publication semantics: relation-logic preservation, subject-aware valuation language, full-sentence slot, conclusion domains, segment perimeter, insider pressure 14:29 Publication integrity: final-claim-only summary, relation logic, typed render slots, valuation relations, evidence domains, trigger ranges 13:40 Guidance label binding: a guidance value must be named by its own concept in its clause 13:16 Prose/trigger cleanup: trend relations, evidence interpretation, clause grammar, render modes, trigger satisfaction 11:09 Relationship layer: a claim's own direction or bound is never written twice 11:03 Relationship layer: RelationshipClaim, typed break-even/story metrics, model-evidence scope, guidance epistemic state, semantic returns, typed blend sources 07:49 SPGI hardening: ordering truth check, comparative vocabulary, trailing sign nouns 07:42 SPGI hardening: trigger magnitude check, implicit comparisons, token-structure rules 07:30 SPGI root-cause remediation: typed units, comparability, corporate actions, StoryBase, discount-rate path, evidence permissions Sep 24 10:49 Fix None growth in canonical pricing view (HON); R5 QA ids need QA context; guidance tolerance + typography; hyphenated horizons benign 10:18 Guidance claims resolve from sealed state; company guidance line in forecast section 09:47 Root-cause remediation: reconciled forecast basis, canonical segments, PricingState, company guidance, ownership/insider permissions, S1-S12 validators 08:10 intrinsic value: headlines only, detail on a tap 07:54 debate: key points as headlines, full point on a tap 07:45 report: findings only, explanatory text removed; home: capability strip removed 05:21 report: full debate (opening cases, rebuttals, PM notes), story and breakeven, sentence-safe key points; mobile: wrapping text claims and card tables Sep 23 22:35 report: disclose a machine-learning price model that is used; plain source names in the blend table 19:41 ML models: walk-forward-judged panel rank, plain-language ML disclosure in report and progress 19:25 UI: roles not models; declutter the home screen 18:32 Summary-first report with expandable sections, mobile UI, live progress (storytellers, debate seats), low-risk stable-rate override 12:34 report: segment-build evidence cited as claims 12:28 Damodaran method: value-weighted business mix, mature-company stable cost of capital, required segment builds 11:43 Filed segment mix from the latest 10-Q/10-K; business-mix beta from Damodaran industry betas; storytellers build segment stories from filings 09:26 NaN is missing data at the claim layer; ownership sentence without a prior-quarter count 09:18 One risk-free source for the story; a missing statistical forecast is a limitation when the story carries the value 
