core/generate
Shay a53ce93acf feat(parser): ADR-0123 comparison-phrasing substrate (substrate-only; lift deferred)
Second parser-expansion ADR after ADR-0122 rate/per-unit. Adds the
comparison algebra substrate (Comparison dataclass + compare_additive /
compare_multiplicative operation kinds + parser patterns + solver /
verifier / pack lemmas) mirroring the substrate-only / lift-deferred
pattern ADR-0122 established.

Substrate
- Comparison(reference_actor, delta: Quantity|None, factor: float|None,
  direction: Literal[more,fewer,times,fraction]) frozen dataclass with
  direction-discriminated delta/factor enforcement and self-reference
  refusal at the Operation boundary
- compare_additive + compare_multiplicative operation kinds admitted in
  VALID_OPERATION_KINDS; Operation.operand widened to Quantity|Comparison
  with kind-discriminated type enforcement; entity-set validation extended
  to cover Comparison.reference_actor
- Parser: _COMPARE_ADDITIVE_RE (more/fewer/less), _COMPARE_TWICE_RE,
  _COMPARE_N_TIMES_RE, _COMPARE_HALF_RE happy-path patterns + 5
  refusal patterns (ambiguous 'N times more', age comparisons,
  combined-with-aggregation, nested additive+multiplicative); inserted
  before _try_initial so leading 'has <N>' shape is not greedily
  consumed as initial possession with unit='more'/'fewer'
- Solver: _apply_compare_additive (refuses on missing reference state,
  overwrite, negative result); _apply_compare_multiplicative (refuses
  on missing reference, ambiguous multi-unit reference, overwrite);
  unit comes from delta.unit (additive) or reference's unique unit
  (multiplicative)
- Verifier: _verify_compare_additive_step + _verify_compare_multiplicative_step
  byte-equal replay; tamper-detects after_value, direction, factor
- Pack: en-arith-006 compare_additive + en-arith-007 compare_multiplicative
  lemmas + glosses; SHA-256 checksums refreshed; manifest 1.0.0 -> 1.1.0;
  provenance tagged adr-0123:comparison_extension:2026-05-23

Measurement (honest; from Gemini empirical sealed run on parallel surface
branch with this substrate)
- Sealed GSM8K correct_rate: 0/1319 (substrate matches zero real cases
  alone). Validates the ADR-0122 multi-construction barrier prediction:
  comparison constructions in GSM8K rarely appear alone — they bind with
  rate (ADR-0124), percentage (ADR-0125), aggregation (ADR-0126), or
  conditional ('if') clauses. First lift signal requires composition.
- Sealed GSM8K wrong: 0 (load-bearing positive claim; ADR-0114a
  Obligation #4 preserved across all 1,319 sealed problems)
- Regression safety: 0 — all 913 non-comparison cases continue to
  refuse exactly as before (refused_parser), no greedy consumption by
  the new comparison patterns

Surface-form catalog (from Gemini Task 2 survey, see ADR doc) covers
6 primary forms across Groups A/B/C; Groups D (age), E (combined with
aggregation), F (nested additive+multiplicative) refused as out-of-scope
with typed ParseError naming the missing companion ADR.

Branch isolation
- Landed via dedicated worktree (feat/adr-0123-substrate from origin/main)
  after a file-race on the shared umbrella branch. Companion surface +
  scaffolding (realizer, ADR doc, tests, README) lands separately as
  feat/adr-0123-surface; orchestrator merges both into the umbrella
  feat/adr-0123-comparison-phrasing.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-23 01:56:28 -07:00
..
__init__.py chore(generate): delete unreachable agenerate (#90) 2026-05-20 19:59:28 -07:00
admissibility.py feat(adr-0026): Phase 3 — ranked admissibility with margin 2026-05-17 15:03:03 -07:00
articulation.py
articulation_legality.py feat(realizer): C1.5 — articulation legality at the realizer boundary 2026-05-20 11:11:28 -07:00
attention.py
bridge_trace.py Phase 1 — bridge trace instrumentation (observation-only) 2026-05-18 18:04:57 -07:00
dialogue.py
discourse_planner.py feat(discourse): Phase 2 — reflective rendering pronominalizes focus subject 2026-05-21 10:16:12 -07:00
exhaustion.py feat(adr-0025): Phase 4 — rotor / frame admissibility at the seam 2026-05-17 15:16:32 -07:00
graph_constraint.py fix(adr-0046): make forward-graph-constraint branch mergeable 2026-05-18 05:57:46 -07:00
graph_planner.py perf(graph): PropositionGraph.topo_order — Kahn's O(N+E) instead of O(N×E) (#92) 2026-05-20 20:37:21 -07:00
grounding_accessors.py feat(grounding): structured GroundedFact accessors for discourse planner 2026-05-19 11:19:59 -07:00
intent.py fix(intent): route 'Actually X R Y' premises to CORRECTION (inference_closure) (#117) 2026-05-22 12:33:56 -07:00
intent_bridge.py Phase 2 — proposition-slot grounding for articulate_with_intent 2026-05-18 18:18:31 -07:00
intent_ratifier.py chore(ratifier): calibrate default ratification threshold 0.0 → 0.5 (#86) 2026-05-20 19:59:25 -07:00
math_parser.py feat(parser): ADR-0123 comparison-phrasing substrate (substrate-only; lift deferred) 2026-05-23 01:56:28 -07:00
math_problem_graph.py feat(parser): ADR-0123 comparison-phrasing substrate (substrate-only; lift deferred) 2026-05-23 01:56:28 -07:00
math_realizer.py feat(parser): ADR-0122 rate/per-unit grammar (substrate-only; lift deferred) 2026-05-22 21:24:28 -07:00
math_solver.py feat(parser): ADR-0123 comparison-phrasing substrate (substrate-only; lift deferred) 2026-05-23 01:56:28 -07:00
math_verifier.py feat(parser): ADR-0123 comparison-phrasing substrate (substrate-only; lift deferred) 2026-05-23 01:56:28 -07:00
morphology.py fix(gaps): close G1+G2+G3 + identity vocab + pipeline safety-stub honour 2026-05-16 21:21:06 -07:00
ood_surface_generator.py feat: ADR-0118a OOD surface generator 2026-05-22 16:49:40 -07:00
operators.py feat(compositionality): compose_relations operator lifts lane 68.8% → 100% 2026-05-16 22:44:06 -07:00
perturbation_suite.py feat: add ADR-0125 perturbation suite 2026-05-22 17:12:33 -07:00
proposition.py feat(adr-0022): Forward Semantic Control — Accepted 2026-05-17 12:10:20 -07:00
realizer.py perf(cognition): hot-path comb pass — 5 mechanical-sympathy fixes (#91) 2026-05-20 20:31:56 -07:00
realizer_guard.py feat(coherence): ADR-0075 — realizer slot-type guard (C1) 2026-05-19 22:35:09 -07:00
render.py
result.py feat(adr-0023): Forward Semantic Control proof evidence — Accepted 2026-05-17 12:55:19 -07:00
rotor_admissibility.py feat(adr-0025): Phase 4 — rotor / frame admissibility at the seam 2026-05-17 15:16:32 -07:00
salience.py
semantic_templates.py feat: vault recall index, Rust versor parity, cognitive pack expansion 2026-05-15 15:34:39 -07:00
stream.py chore(generate): make stop-tokens caller-overridable via RuntimeConfig (#87) 2026-05-20 19:59:33 -07:00
surface.py feat(surface): ADR-0031 — score-decomposition surface (per-axis hedges) 2026-05-17 20:16:22 -07:00
templates.py feat(realizer): C1.5 — articulation legality at the realizer boundary 2026-05-20 11:11:28 -07:00