Merge remote-tracking branch 'origin/main' into hf-deploy

dashboard: add #harness + #harness-appendix sections (v3 design integration)

docs(judge): writeup draft v1 — methodology arc + position + v1.2 fix-list

calibrate(jury): 4A characterizes v1.1.1 residual as model-class-specific

calibrate(jury): v1.1+v1.1.1 — fix weighting bugs; recency-position paraphrase clause

rubric: clarify groundedness reference scope (snippets-only) for v1.1 gold (#20)

fix(calibration): per-corpus dispatch in generate-outputs (#19)

Merge pull request #18 from tyy0811/feat/judge-layer-v1

fix(types): four mypy errors blocking CI

docs(harness,readme): two re-review must-fix items

fix(judges,calibration,harness): three Codex adversarial-review findings

fix(judges,calibration): five review follow-ups (items 5, 6, 7, 9, 10)

fix(judges): four review-blocking bugs (review items 1–4 + 8)

docs+build: judge-layer v1 coupled-artifact updates

refactor(metrics): delete superseded LLM judges (answer_faithfulness etc.)

refactor(harness): migrate to per-dimension Judge layer (drop faithfulness/correctness)

feat(config): add evaluation.judge_dimensions field

feat(calibration): generate_kappa_table with strict/warn modes

feat(scripts): run_calibration.py orchestrator for Steps A/C/D

feat(calibration): six row configs for the κ ablation table

feat(goldens): add source_snippets to 8 FastAPI calibration items

feat(calibration): 30-item stratified calibration_v1 sample

test(calibration): sklearn-parity fixtures + cross-check CI test

feat(calibration): hand-rolled cohen_kappa, gwets_ac2, bootstrap_ci

feat(variance): PermutedJudge + Jury — N permutations and multi-judge aggregator

feat(judges): CitationFaithfulnessJudge with all-or-nothing aggregation

feat(judges): CompletenessJudge + three-point reference-based rubric

feat(judges): RelevanceJudge + anchored three-point rubric

feat(judges): GroundednessJudge + anchored binary rubric

feat(judges): _call_judge_with_retry helper with strict-reprompt + abstain

feat(judges): MockJudge with LookupError on missing keys

feat(judges): Judge ABC with judge_id derived from model + dimension

feat(judges): Rubric markdown loader with aggressive validation

feat(judges): ScoreResult + abstain-reason constants

test: scaffold tests/evaluation/ directory for judge-layer tests

ci: document zero-secret contract on test job with empty env block

chore(tooling): exclude scripts/_dev/ from ruff and mypy

docs(plans): judge-layer v1 implementation plan — 12 phases, ~50 tasks

docs(plans): judge-layer v1 design — supersede continuous-scale judges with discrete-anchored 2-judge jury + κ-validated calibration

docs(readme): correct test count 444 → 443

Merge remote-tracking branch 'origin/main' into hf-deploy

Merge pull request #17 from tyy0811/dashboard-v3

Redesign landing page: paper+ink visual system, instrumented pipeline, OWASP badges

Merge remote-tracking branch 'origin/main' into hf-deploy

Merge pull request #16 from tyy0811/feat/chip-row-owasp-coverage-subtitle

feat(landing): OWASP coverage subtitle + LLM05 tooltip on corpus chips

Merge remote-tracking branch 'origin/main' into hf-deploy

Merge pull request #15 from tyy0811/docs/security-llm07-residual-risk

docs(security): LLM07 named residual risk — injection classifier coverage gap

Merge remote-tracking branch 'origin/main' into hf-deploy