core/evals/gsm8k_math/equivalence
2026-07-08 20:01:43 -07:00
..
v1 feat: unify 3-core-language depth into PropositionGraph spine and fix math/parity tests 2026-07-08 20:01:43 -07:00
__init__.py test(derivation): add ADR-0184 semantic replay equivalence harness 2026-06-10 14:35:22 -07:00
trace.py test(derivation): add ADR-0184 semantic replay equivalence harness 2026-06-10 14:35:22 -07:00