2e4e45b49b
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.
|
||
|---|---|---|
| .. | ||
| architecture | ||
| decisions | ||
| sessions | ||
| capability_roadmap.md | ||
| eval_methodology.md | ||
| PROGRESS.md | ||
| runtime_contracts.md | ||
| RUST.md | ||
| Whitepaper.md | ||
| Yellowpaper.md | ||