core/evals/grammatical_coverage/dev
Shay f5f3603dcb feat(evals): Phase 1 grammatical-coverage lane setup
Establish the grammatical-coverage eval lane with 13 English v1
constructions (simple declarative, negation, conjunction, disjunction,
embedded clause, relative clause, quantification, tense, aspect).

- contract.md with scoring rubric and pass thresholds
- runner.py conforming to framework interface
- dev set: 41 cases (baseline: 24.4%, only C01/C10 pass)
- public v1: 36 cases (baseline: 19.4%, only C01/C10 pass)
- holdout and realizer engineering are next

The realizer currently handles only simple present-tense SVO declaratives.
Negation, conjunction, embedding, quantification, tense, and aspect all
need engineering work.
2026-05-16 05:45:14 -07:00
..
cases.jsonl feat(evals): Phase 1 grammatical-coverage lane setup 2026-05-16 05:45:14 -07:00