Fetching metadata from the HF Docker repository...
-
Fundamentals table: compact headers + provenance footnotes; print-safe tables
-
intrinsic value: headlines only, detail on a tap
-
debate: key points as headlines, full point on a tap
-
report: findings only, explanatory text removed; home: capability strip removed
-
home: capability strip below the search
-
home: polished tagline
-
home: 'Forged by AI. Tested under fire.'
-
home: 'Seven AIs. One verdict.' with ML capability tags
-
home: multi-model AI headline
-
report: full debate (opening cases, rebuttals, PM notes), story and breakeven, sentence-safe key points; mobile: wrapping text claims and card tables
-
ML models: walk-forward-judged panel rank, plain-language ML disclosure in report and progress
-
UI: roles not models; declutter the home screen
-
Storytellers run in parallel; 'under the hood' progress narration of Damodaran's framework inputs
-
progress: story-start marker, updated timings; summary limited to two figures
-
Summary-first report with expandable sections, mobile UI, live progress (storytellers, debate seats), low-risk stable-rate override
-
AnalysisState pipeline: reconciliation, staged validation, frozen state, claim-token prose, audited renderer; public/QA split
-
UI reads the shared objects: ScenarioSet, structured triggers, three named signals, engine methodology
-
Architecture: typed concepts + immutable AnalysisContext with rejected-field quarantine and lineage; applicability policy; valuation engines with label invariants; quant reliability states; semantic comparisons; engine-side synthesis/scenario EV; five-state checks; six publication gates incl. final render audit; property/golden/corruption tests
-
Remediation round 2: bank gross/net revenue mapping, REIT/financial composite exclusions, ADS ratio on issuer, total-return check per sentence, target-multiple phrasing in forward P/E audit, SOTP warning
-
Pipeline remediation P0: canonical layer (issuer typing, framework selection, metric lineage, SEC XBRL cross-checks, Stage A validation), consensus-availability handling, story bridge/dispersion, corporate-action state machine, quote/return-kind rules, two-stage publication gate, guardrail tests
-
Report-level validation gate: canonical rating, reproducible blend/composite audits, canonical PEG, Form 4 insider context, SEC-first leadership, mechanical momentum, REIT/services split, markdown export
-
Upload static/index.html with huggingface_hub
-
Upload static/app.css with huggingface_hub
-
Upload static/app.js with huggingface_hub
-
Upload static/index.html with huggingface_hub
-
Upload static/app.js with huggingface_hub
-
Upload static/index.html with huggingface_hub
-
Upload static/app.css with huggingface_hub
-
Upload static/app.js with huggingface_hub
-
Upload static/index.html with huggingface_hub
-
Upload static/app.js with huggingface_hub
-
Upload static/index.html with huggingface_hub
-
Upload static/app.css with huggingface_hub
-
Upload static/app.js with huggingface_hub
-
Upload static/index.html with huggingface_hub
-
Upload static/app.css with huggingface_hub
-
Upload static/index.html with huggingface_hub
-
Upload static/app.js with huggingface_hub
-
Upload static/app.css with huggingface_hub
-
Upload static/index.html with huggingface_hub
-
Upload static/app.css with huggingface_hub
-
Upload static/app.js with huggingface_hub
-
Upload static/index.html with huggingface_hub
-
Upload static/app.css with huggingface_hub
-
Upload static/app.js with huggingface_hub
-
Upload static/index.html with huggingface_hub
-
Upload static/app.js with huggingface_hub
-
Upload static/index.html with huggingface_hub
-
Upload static/app.js with huggingface_hub
-
Upload static/index.html with huggingface_hub
