core/evals
Shay 2e4e45b49b feat(evals): provenance lane v1 — replay determinism + source back-pointers
Phase 2's first lane: every articulated claim must back-point to one of
{pack axiom, vault entry, teaching event}, and replay must reproduce the
trace bit-for-bit.

Components:
- core/cognition/provenance.py: Provenance dataclass + compute_provenance()
  deriving sources from a CognitiveTurnResult. Pack source = non-UNKNOWN
  intent.tag (pack-defined intent rule matched); vault source = vault_hits
  count; teaching source = pack_mutation_proposal.proposal_id.
- evals/provenance/{contract.md, runner.py, dev/, public/v1/, holdouts/v1/}:
  45 cases across pack_axiom / vault_recall / teaching / mixed categories.
- tests/test_provenance.py: 6 unit tests covering all source-kind profiles.

Sub-metrics (all four must pass):
- replay_determinism: same input + fresh runtime -> same trace_hash
- input_sensitivity: distinct prompts -> distinct trace_hashes
- source_attribution: every expected source kind present in Provenance
- source_validity: every cited source resolves to a real artefact

Results:
- dev: 10/10 (all sub-metrics 1.0)
- public/v1: 20/20 (all sub-metrics 1.0)
- holdouts/v1: 15/15 (all sub-metrics 1.0)

PROGRESS.md updated to mark Phase 2 in progress with provenance v1 complete.
2026-05-16 11:45:00 -07:00
..
cognition feat(evals): Phase 0 — benchmark methodology lock-in and eval framework 2026-05-15 22:36:53 -07:00
grammatical_coverage feat(evals): grammatical-coverage v2 cases - 36 cases with deeper nesting and rarer vocabulary (100% pass) 2026-05-16 06:40:55 -07:00
identity_divergence feat(evals): identity-divergence lane v1 - 93 curriculum events, two axis profiles (Precision/Generosity), divergence/coherence/causal metrics (all pass) 2026-05-16 06:48:13 -07:00
provenance feat(evals): provenance lane v1 — replay determinism + source back-pointers 2026-05-16 11:45:00 -07:00
reports Add cognitive eval harness and calibration replay (#30) 2026-05-15 07:41:36 -07:00
zero_code_domain_acquisition feat began creation of zero code domain acquisition. did not complete yet. 2026-05-16 06:31:01 -07:00
__init__.py Add cognitive eval harness and calibration replay (#30) 2026-05-15 07:41:36 -07:00
baseline_runner.py feat(evals): Phase 0 — benchmark methodology lock-in and eval framework 2026-05-15 22:36:53 -07:00
cognition_cases.jsonl feat: vault recall index, Rust versor parity, cognitive pack expansion 2026-05-15 15:34:39 -07:00
framework.py feat(evals): Phase 0 — benchmark methodology lock-in and eval framework 2026-05-15 22:36:53 -07:00
holdout_runner.py feat(evals): Phase 0 — benchmark methodology lock-in and eval framework 2026-05-15 22:36:53 -07:00
metrics.py Add cognitive eval harness and calibration replay (#30) 2026-05-15 07:41:36 -07:00
run_cognition_eval.py Add cognitive eval harness and calibration replay (#30) 2026-05-15 07:41:36 -07:00