core/docs
Shay 2fcd22c319
docs(ADR-0164.2): pronoun/entity resolution policy (#319)
Proposed sub-ADR under ADR-0164 resolving Open question #3.

- Reviews existing _resolve_question_entity heuristic in
  generate/math_candidate_parser.py: refuse-on-ambiguity is correct,
  but flat-document whitelist scan misses recency, kinship entities,
  group antecedents from conjunction, and names absent from the
  closed name lists.
- Specifies EntityRegistry as a field on ProblemReadingState
  (ADR-0164.3 companion): append-only entries with canonical name,
  inferred gender + source, mention positions, and relational anchor
  for kinship entities.
- Two refusal-first ambiguity rules: ambiguous_pronoun_referent (R1,
  recency tiebreaker within RECENCY_GAP_MIN refuses) and
  unresolved_pronoun (R2).
- Worked walk-through on five GSM8K train_sample cases (0001 Tina,
  0010 Yun/Marion, 0027 Malcolm, 0017 Jason/Eric, 0033 Rachel + kin).
- Three policy-vs-heuristic disagreements (D1 Jason/Eric him; D2
  Georgie he via single-salient back-fill; D3 Aaron/Carson they via
  GROUP entry) all turn refusals into correct resolutions, plus one
  counter-direction D4 where new policy is principled-conservative.
- Preserves wrong = 0 by construction at every branch.
2026-05-26 19:32:19 -07:00
..
adr
architecture
audit fix(phase2): close W-006/W-010/W-013/W-014/W-019 operator decisions (#270) 2026-05-25 11:34:19 -07:00
briefs feat(W-019): learning-arc demo — engine-authored proposal from contemplation (ADR-0152) (#276) 2026-05-25 13:03:10 -07:00
curriculum
decisions docs(ADR-0164.2): pronoun/entity resolution policy (#319) 2026-05-26 19:32:19 -07:00
evals
handoff
implementation docs: propose semantic-symbolic binding graph layer (#170) 2026-05-23 09:58:39 -07:00
plans docs(plan): add CORE general advancement path (#314) 2026-05-26 18:32:08 -07:00
sessions docs(session): 2026-05-26 corridor closure — first GSM8K lift + workbench operational (#305) 2026-05-26 13:49:08 -07:00
workbench feat(W-028): chat surface + trace drawer (#303) 2026-05-26 13:22:11 -07:00
admissibility-exemplars.md feat(ADR-0163.B.2): four new exemplar corpora — discrete_count_statement, multiplicative_aggregation, currency_amount, plus temporal_aggregation v2 widening (#306) 2026-05-26 14:36:59 -07:00
capability_roadmap.md docs: Phase 5 GSM8K-math substrate completion sweep (ADR-0119 + sub-phases + ADR-0114a 10/10) 2026-05-22 20:39:24 -07:00
ethics_packs.md
EVAL_AUDIT_2026-05-20.md
eval_methodology.md
formation_pipeline_plan.md
frontier_baselines.md
gaps.md
hitl-backpressure.md feat(ADR-0161.3): submission-time invariants — duplicate + dependent_on_pending auto-reject (#313) 2026-05-26 16:46:25 -07:00
holdout_recipients.txt
identity_packs.md
master-plan-post-substrate-audit.md docs(session): 2026-05-26 corridor closure — first GSM8K lift + workbench operational (#305) 2026-05-26 13:49:08 -07:00
pack_inventory_2026-05-21.md
PROGRESS.md docs(session): 2026-05-26 corridor closure — first GSM8K lift + workbench operational (#305) 2026-05-26 13:49:08 -07:00
recognizer-registry.md feat(ADR-0163.D): wire ratified RecognizerSpecs into math_candidate_graph admissibility surface (#302) 2026-05-26 13:11:47 -07:00
refusal-taxonomy.md feat(ADR-0163.A): refusal taxonomy lane — shape categorization of GSM8K admissibility gaps (#297) 2026-05-26 11:27:11 -07:00
reviewers.yaml fix(quarantine): drain all 60 quarantined tests — QUARANTINE=∅ (#267) 2026-05-25 11:22:12 -07:00
runtime_contracts.md docs: Phase 5 GSM8K-math substrate completion sweep (ADR-0119 + sub-phases + ADR-0114a 10/10) 2026-05-22 20:39:24 -07:00
RUST.md
safety_packs.md
teaching_order.md
test-debt-quarantine.md ci: full-pytest gate + QUARANTINE registry (49 known failures, uv) (#263) 2026-05-25 06:21:04 -07:00
truth_seeking_schema.md
Whitepaper.md docs: Phase 5 GSM8K-math substrate completion sweep (ADR-0119 + sub-phases + ADR-0114a 10/10) 2026-05-22 20:39:24 -07:00
Yellowpaper.md docs: Phase 5 GSM8K-math substrate completion sweep (ADR-0119 + sub-phases + ADR-0114a 10/10) 2026-05-22 20:39:24 -07:00