Fetching metadata from the HF Docker repository...
Sep 28 18:36 Claim lineage: typed guidance/engine-vs-consensus relations, lineage checks, HistoricalMetricQuality label 17:54 Story peak share printed to two decimals so market size x share reproduces revenue 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 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 19:38 Guidance basis label: only guidance rows with typed values (a trigger may cite a plain metric claim) 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 17:52 FULL_SENTENCE relation form is template-only; frontier framing is a valid paraphrase 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 13:16 Prose/trigger cleanup: trend relations, evidence interpretation, clause grammar, render modes, trigger satisfaction 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 10:18 Guidance claims resolve from sealed state; company guidance line in forecast section 10:06 Guidance by filing-header document type; signed 13F change claim 10:01 Guidance exhibit matching + retries; outlier trim vs median of all methods; margin-change claims; motive rule scoped to trades 09:47 Root-cause remediation: reconciled forecast basis, canonical segments, PricingState, company guidance, ownership/insider permissions, S1-S12 validators 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 19:41 ML models: walk-forward-judged panel rank, plain-language ML disclosure in report and progress 12:28 Damodaran method: value-weighted business mix, mature-company stable cost of capital, required segment builds 09:26 NaN is missing data at the claim layer; ownership sentence without a prior-quarter count 08:49 Damodaran datasets wired in: monthly implied ERP (auto-refresh), country risk premiums, bottom-up industry betas, industry sales-to-capital and margins; market-built cost of equity in the cross-sectional DCF 08:00 Damodaran life cycle: consensus-based staging; story FCFF for every operating company; capital release, distress value and zero stable growth in decline; 13F ownership as a state namespace Sep 22 20:45 One rating table; typed thesis triggers; rating-word and gap-direction ingestion rules; clause-bounded labels 20:24 AnalysisState pipeline: reconciliation, staged validation, frozen state, claim-token prose, audited renderer; public/QA split 
