core/evals/gsm8k_math/train_sample
Shay 684481910b
audit(ADR-0136.S.2): refusal rescan v2 — barrier-shift ledger, subsumption directive pinned (#205)
Measurement-only branch. Re-runs parse_and_solve on all 50 GSM8K train-sample
cases against the current parser (post-S.1/S.2) and produces a barrier-shift
ledger comparing v1 taxonomy to current behavior.

Results: admitted=3/50 (0014, 0018, 0042), wrong=0, barrier_shifted=27/50.
Context-filler dominance collapsed from 23→3 cases; compound_statement (6)
and novel_initial_form (5) are now the largest buckets.

Subsumption directive pinned: ADR-0137 SHALL re-derive all short-circuit
admissions as (DeferredCandidate, evidence, BindingProof) triples.
2026-05-23 21:43:25 -07:00
..
v1 audit(ADR-0136.S.2): refusal rescan v2 — barrier-shift ledger, subsumption directive pinned (#205) 2026-05-23 21:43:25 -07:00
__init__.py feat(gsm8k): ADR-0126 P6 — train-sample runner + exit-criterion gate 2026-05-23 06:33:06 -07:00