Decision ·
Primary metric = raw ratio, bar > 0.50 (the author's decision on 2026-10-02, not the app maintainer's)
From the record
- Context
- Direction: "eval + pipeline technique" (better answers from the same model)
- Reversible
- —
- Status
- superseded by D-036 · Floor-adjusted ratio + win/tie/loss became the headline on 2026-10-06 (applied 2026-10-07); the raw rule is still printed as the formal rule.
- Alternatives considered
- floor-aware metric
Linked facts · 1
- Primary metric = raw ratio, bar > 0.50 (the author's decision on 2026-10-02, not the app maintainer's)Primary metric = raw ratio, bar > 0.50 (the author's decision on 2026-10-02, not the app maintainer's)Date2026-10-02Kinda record, not a measurement (set, status, judge, n, seeds: not recorded)Caveatthe scrubbed public plan says 'the maintainer's decision', but the private original names the author; in the publication 'the app maintainer' means the upstream maintainer, so write 'the author's decision'Sourcebenchmark
bench/v0.3/plan/analysis-plan.md:17Open the data file