← polyphony · eval · frankenstein · ci
polyphony · claude-opus-5-5
✗ failincomplete: no scored casesMetrics
| attribution.score | 0.533 (was 0.267) |
Labels
| cadence | on-demand |
| experiment | w16-attribution-redraw |
| harness_sha | 7cc53fec143420b02f4740b4a733a7115b62d6c0 |
| judge_provider | groq |
| judge_self_graded | False |
| repeat | 3 |
| trigger | workflow_dispatch |
Compared with the previous run
Baseline 2026-10-24 06:21 UTC · 100% → this run 0% · code diff ↗
± score moved · 1
- eval:attribution: 0.27 → 0.53
cases added / removed
- − eval:continuity
- − eval:extraction
- − eval:ingestion
- − eval:retrieval
Cases (1)
eval:attribution0.53 · reported
score=0.533repeats=3score_std=0.082
Output
score=0.5333 ±0.0816 (n=3) accuracy=0.4333 chance=0.3333 n=30