core/evals
Shay 1f90cb6cf6
feat(ADR-0114a.6): depth-curve auditor — Obligation #6 wired for B3 (assertion holds, coverage gap named) (#190)
Implements the external auditor for ADR-0114a Obligation #6:
"depth_curve.py produces a per-bucket curve;
accuracy(N) >= accuracy(depth_1) * (1 - eps)^(N - 1) for eps = 0.05."

Mirrors PR #189's auditor pattern (re-runs lane via the candidate-
graph pipeline, aggregates over committed cases, emits deterministic
report). Uses len(trace.steps) as the authoritative depth — the
engine's actually-executed reasoning, not the case's declared depth.

New module core/capability/depth_curve.py:
  - Bucket schema mirrors ADR-0119.6: depth_1, depth_2-3,
    depth_4-5, depth_6-8. Depth > 8 raises rather than silently
    extending. Depth == 0 (initial-only problems) skipped — nothing
    to decay.
  - representative_depth = min(bucket) — most permissive bound
    convention; tightening requires an ADR amendment.
  - epsilon = 0.05 pinned per ADR-0120 §Threshold rationale.
  - Two-axis verdict: obligation_6_mechanism_wired (always true if
    auditor ran), obligation_6_assertion_holds (every populated
    bucket satisfies the decay bound), coverage_sufficient (>=2
    buckets populated AND >=3 cases each — required for the
    assertion to be statistically meaningful).

CLI: core capability depth-curve (added to core/cli.py).
Writes evals/obligation_6_depth_curve/<lane_id>.json.

Empirical verdict on current main:
  lane:                B3_bounded_grammar
  cases_total:         50
  cases_solved:        22
  mechanism_wired:     True
  assertion_holds:     True
  coverage_sufficient: False
  populated:           [depth_1 (21/21=1.0000), depth_2-3 (1/1=1.0000)]

Both populated buckets satisfy the decay bound. Coverage gap is
honestly named in the refusal_reason: depth_2-3 has only 1 case,
depth_4-5 and depth_6-8 have none. This is B3-owner work (case
authoring under the existing grammar contract), not auditor work;
reserved as a B3 v1.1 follow-up PR.

Honest scope-limit: B3 only. B1 (algebra, no trace) and B2 (chain
validation, not problem-solving) need different metrics — separate
sub-ADRs.

Trust boundary: read-only access to B3 cases + transitive pack
reads via the pipeline; single deterministic write to artifact path.

Tests: 24/24 covering bucket schema closure (depth 1..8 + raise on
9+), decay bound math (epsilon pinned, formula correct, depth_1 has
no bound), coverage-sufficient policy (thresholds pinned), lane
evaluation (passes on real B3 + refuses on missing cases),
coverage-sufficient distinction (B3 today vs synthetic 5+5 fixture
showing both pass), determinism (report identical + artifact
byte-equal).
2026-05-23 16:19:58 -07:00
..
adversarial_identity
anchor_lens_tour parallel eval runner (#46) 2026-05-19 23:51:59 -07:00
anti_regression chore(evals): contracts + bench json + Lane B viewer + chart + audit + demo schema (#62) 2026-05-20 13:53:13 -07:00
articulation feat(demo): core demo articulation — discourse-planner spine, end-to-end 2026-05-19 13:41:24 -07:00
articulation_of_status
audit_tour
calibration
classical_literature_ood
cognition parallel eval runner (#46) 2026-05-19 23:51:59 -07:00
cold_start_grounding feat(evals+bench): isolation lanes, holdouts, planner-on bench sub-bench 2026-05-19 12:42:55 -07:00
compositionality
compound_intent_decomposition feat(evals+bench): isolation lanes, holdouts, planner-on bench sub-bench 2026-05-19 12:42:55 -07:00
contradiction_detection
conversation feat(demo): humanise teaching-grounded surface for layperson display 2026-05-19 14:14:02 -07:00
conversational_thread_coherence feat(evals+bench): isolation lanes, holdouts, planner-on bench sub-bench 2026-05-19 12:42:55 -07:00
cross_domain_transfer
curriculum_loop_closure feat(evals): ADR-0105 — sealed holdout encryption via age (#108) 2026-05-22 10:09:43 -07:00
demo_composition feat(demos): implement ADR-0098 — Demo Composition Contract 2026-05-21 19:02:29 -07:00
deterministic_fluency feat(evals): deterministic_fluency lane — six structural predicates 2026-05-19 07:16:44 -07:00
discourse_paragraph
domain_contract_validation feat(capability): implement ADR-0093 — Domain Pack Contract v1 wired in 2026-05-21 18:33:23 -07:00
elementary_mathematics_ood feat(capability): ADR-0110 promote mathematics_logic to expert_demo (#118) 2026-05-22 12:59:23 -07:00
english_fluency_ood
fabrication_control feat: ADR-0119.1 — seal fabrication_control holdout with age encryption (Obligation #1) 2026-05-22 17:22:46 -07:00
forward_semantic_control
foundational_biology_ood
foundational_physics_ood feat: ADR-0111 physics expert-demo promotion (second successful) 2026-05-22 14:37:36 -07:00
frontier_compare feat(contemplation): land ADR-0080 phase 1 (#119) 2026-05-22 13:10:03 -07:00
grammatical_coverage
gsm8k_math feat(ADR-0131.G.3.1): numerics extensions — fractions + multi-currency + multi-token cardinals + word-num-adjective 2026-05-23 15:16:46 -07:00
gsm8k_parser_dev feat: add ADR-0125 perturbation suite 2026-05-22 17:12:33 -07:00
hebrew_fluency feat(packs): ADR-0103 — attach hebrew_fluency + koine_greek_fluency lanes to ADR-0102 (#106) 2026-05-22 09:43:46 -07:00
identity_divergence
industry_demos evals/industry_demos: add run_all.py suite runner 2026-05-21 08:23:29 -07:00
inference_closure feat: ADR-0122 systems_software audit-passed deferred (lane-shape mismatch) 2026-05-22 16:31:59 -07:00
introspection
koine_greek_fluency feat(packs): ADR-0103 — attach hebrew_fluency + koine_greek_fluency lanes to ADR-0102 (#106) 2026-05-22 09:43:46 -07:00
lab research(evals): phi separation probe for ADR-0081 follow-up (#57) 2026-05-20 12:34:59 -07:00
learning_loop chore(evals): contracts + bench json + Lane B viewer + chart + audit + demo schema (#62) 2026-05-20 13:53:13 -07:00
long_context_cost chore(evals): contracts + bench json + Lane B viewer + chart + audit + demo schema (#62) 2026-05-20 13:53:13 -07:00
math_bounded_grammar/v1 feat(ADR-0131.3): bounded-grammar word-problem benchmark — lane PASSED 50/50 (#180) 2026-05-23 11:27:04 -07:00
math_capability_axes feat(G1): verb-classes capability axis (ADR-0131.G.1) 2026-05-23 15:39:14 -07:00
math_expert_claims/v1 feat(ADR-0131.4): composite math-expert promotion gate — wired, evaluated, PASSING 2026-05-23 15:23:14 -07:00
math_symbolic_equivalence feat(ADR-0131.1.F): frontier-baseline comparison harness for B1 (#178) 2026-05-23 12:14:06 -07:00
math_teaching_corpus/v1 feat(ADR-0131.2.B): B2 teaching-corpus enrichment — load-bearing gate (#177) 2026-05-23 11:29:48 -07:00
miner_loop_closure feat(teaching): implement ADR-0095 — Miner-Sourced Teaching Proposals 2026-05-21 18:18:51 -07:00
monotonic_learning
multi_agent_composition
multi_sentence_response feat(evals+bench): isolation lanes, holdouts, planner-on bench sub-bench 2026-05-19 12:42:55 -07:00
multi_step_reasoning
obligation_5_perturbation feat(ADR-0114a.5): reasoning-isolation perturbation suite — Obligation #5 wired for B3, PASSING 130/130 preserving, 68/68 breaking (#191) 2026-05-23 16:07:59 -07:00
obligation_6_depth_curve feat(ADR-0114a.6): depth-curve auditor — Obligation #6 wired for B3 (assertion holds, coverage gap named) (#190) 2026-05-23 16:19:58 -07:00
obligation_8_adversarial feat(ADR-0114a.8): adversarial auditor — Obligation #8 wired, PASSING; surfaces 2 known parser-layer gaps (#192) 2026-05-23 16:11:37 -07:00
obligation_10_pack_provenance feat(ADR-0114a.10): pack-provenance auditor — Obligation #10 wired for B3, PASSING 2026-05-23 15:44:53 -07:00
orthogonality_tour parallel eval runner (#46) 2026-05-19 23:51:59 -07:00
prompt_diversity feat(adr-0085): gloss-aware CAUSE composer — explanation frame from glosses (#70) 2026-05-20 15:55:08 -07:00
provenance
public_demo feat: ADR-0111 physics expert-demo promotion (second successful) 2026-05-22 14:37:36 -07:00
realizer_guard chore(evals): contracts + bench json + Lane B viewer + chart + audit + demo schema (#62) 2026-05-20 13:53:13 -07:00
refusal_calibration
register_diagnostics feat(evals): per-intent register-firing diagnostic + CI gate + tests (#103) 2026-05-21 07:05:23 -07:00
register_tour feat(register): ADR-0077 — substantive register knobs + layering boundary (R6) 2026-05-19 23:39:11 -07:00
reports
results feat: ADR-0086 + ADR-0087 + 100-register catalog — cognition lane closure 2026-05-21 00:08:12 -07:00
reviewer_registry feat(capability): implement ADR-0092 — Reviewer Registry v1 2026-05-21 18:01:24 -07:00
sample_efficiency
self_consistency_over_time feat(runtime+evals): warm-path pack grounding + three long-span lanes 2026-05-19 08:26:38 -07:00
symbolic_logic feat: ADR-0122 systems_software audit-passed deferred (lane-shape mismatch) 2026-05-22 16:31:59 -07:00
teaching_injection_resistance
walkthrough_chain feat(evals+bench): isolation lanes, holdouts, planner-on bench sub-bench 2026-05-19 12:42:55 -07:00
warmed_session_consistency feat(evals+bench): isolation lanes, holdouts, planner-on bench sub-bench 2026-05-19 12:42:55 -07:00
zero_code_domain_acquisition
__init__.py
_parallel.py parallel eval runner (#46) 2026-05-19 23:51:59 -07:00
baseline_runner.py
CLAIMS.md chore(evals): contracts + bench json + Lane B viewer + chart + audit + demo schema (#62) 2026-05-20 13:53:13 -07:00
cognition_cases.jsonl
framework.py feat(evals): ADR-0105 — sealed holdout encryption via age (#108) 2026-05-22 10:09:43 -07:00
holdout_runner.py feat(evals): ADR-0105 — sealed holdout encryption via age (#108) 2026-05-22 10:09:43 -07:00
metrics.py
parallel.py parallel eval runner (#46) 2026-05-19 23:51:59 -07:00
run_cognition_eval.py parallel eval runner (#46) 2026-05-19 23:51:59 -07:00