2 commits

Author	SHA1	Message	Date
Shay	1395ec1354	feat(packs): ADR-0103 — attach hebrew_fluency + koine_greek_fluency lanes to ADR-0102 (#106) ... * feat(evals): add Hebrew fluency holdout cases * feat(evals): add Koine Greek fluency holdout cases * feat(packs): attach fluency lanes to he_core_cognition_v1 * feat(packs): attach fluency lanes to he_logos_micro_v1 * feat(packs): attach fluency lanes to grc_logos_cognition_v1 * feat(packs): ADR-0103 fluency lane attachment * test(packs): expect ADR-0103 fluency lanes on Hebrew Greek contracts * docs(evals): add Hebrew fluency holdout split note * docs(evals): add Koine Greek fluency holdout split note * docs(evals): note Hebrew holdout attachment * docs(evals): note Koine Greek holdout attachment * docs: add ADR 0103 placeholder * docs(adr): expand ADR-0103 fluency lane attachment * docs: index ADR-0103 and refresh frontier	2026-05-22 09:43:46 -07:00
Shay	ad7993e861	feat(phase5): land 5.2–5.7 — six new fluency lanes, parallel sweep ... Completes the Phase 5 curriculum-era lane checklist alongside 5.1. English-substrate domain lanes (5.4–5.7) — extend the proven english_fluency_ood pattern with new vocabulary domains. Same 13-construction realizer, same grammatical_coverage rubric, new triples. All four lanes land at 100% on both splits: 5.4 elementary_mathematics_ood 117/117 public + 39/39 holdouts domains: arithmetic, set, geometry | holdout: probability 5.5 foundational_physics_ood 117/117 + 39/39 domains: mechanics, electricity, thermodynamics | holdout: optics 5.6 foundational_biology_ood 117/117 + 39/39 domains: cell, organism, ecosystem | holdout: genetics 5.7 classical_literature_ood 117/117 + 39/39 domains: epic, tragedy, lyric | holdout: comedy New-language lanes (5.2 Hebrew, 5.3 Koine Greek) — scoped honestly to v1 = C01 only, script + length rubric. The realizer's tense/aspect/quantifier/negation logic in generate/templates.py is English-only; C02-C13 in HE/GRC requires Hebrew/Greek morphology + rhetorical templates, named explicitly in each lane's gaps.md as the v2 unblock path. v1 measures what infrastructure exists: 5.2 hebrew_fluency 3/3 (predicate-subject-object assembly, Hebrew script gate) 5.3 koine_greek_fluency 3/3 (subject-object-predicate assembly, Greek script gate) Lane scaffolds follow the established pattern: contract.md, runner.py, __init__.py, gaps.md, public/v1/cases.jsonl, dev/cases.jsonl, holdouts/v1/cases.jsonl (5.4–5.7 only; HE/GRC holdouts deferred to v2 when vocabulary expands). Generators + scorers: scripts/generate_phase5_domain_lanes.py — 5.4–5.7 case emit scripts/scaffold_phase5_domain_lanes.py — 5.4–5.7 contracts/runners scripts/generate_phase5_language_lanes.py — 5.2/5.3 case emit scripts/score_phase5_holdouts.py — parallel holdouts scoring via multiprocessing.Pool (mirrors the parallel-eval pattern from evals/parallel.py) Lanes are wired into core eval --list automatically through the framework's lane discovery; parallel sweeps via bash background jobs (one process per lane). Regression clean: smoke 54, runtime 19, teaching 17, packs 6, cognition 57, algebra 132. Cognition eval 100% across all metrics.	2026-05-16 20:59:31 -07:00