polyphony · claude-opus-5-5
✓ pass≠ not comparableMetrics
| prose.score | 0.992 (was 0.935) |
| prose.words | 3,607 (was 3,632) |
Labels
| cadence | on-demand |
| experiment | w16-r2-2 |
| harness_sha | 6e14ad391bad41461cd8f8dc76e7871476724003 |
| judge_provider | groq |
| judge_self_graded | False |
| repeat | 1 |
| trigger | workflow_dispatch |
Compared with the previous run
Baseline 2026-10-24 09:36 UTC · 100% → this run 100% · code diff ↗
- eval:prose: 0.93 → 0.99
Cases (1)
words=3607 path=planned rubrics={'R1': 1.0, 'R2': None, 'R3': 1.0, 'R4': 0.975, 'R5': 1.0} seams=0/0scene 1 R1: All required canon characters appear correctly and behave as described, with no extraneous or mischaracterized figures. | scene 1 R3: All five planned beats appear in the correct order with their specified changes and no unplanned major events. | scene 1 R4: The scene maintains consistent first‑person limited POV, past tense, and the gracious yet uneasy tone throughout, with varied concrete sentences and no structural violations. | scene 1 R5: The prose aligns with canon and planned beats, containing no contradictions and includes all intended details. | scene 1 R2: not applicable: under two cast speakers with voice samples have attributed lines | scene 2 R1: All required principal characters (Aldous Kerr and Count Vasska) appear correctly with proper names and behavior, and no unauthorized characters are introduced. | scene 2 R3: All five planned beats appear in correct order with their required changes and no extra unplanned events. | scene 2 R4: The scene maintains consistent Aldous POV and past tense, matches tone, and is a polished narrative without prohibited formatting. | scene 2 R5: The passage aligns with canon and planned beats, contains no contradictions, and fulfills the continuity criteria fully. | scene 2 R2: not applicable: under two cast speakers with voice samples have attributed lines | scene 3 R1: All required canon characters appear correctly with proper behavior and no extraneous or mischaracterized figures. | scene 3 R3: All planned beats appear in the correct order with the specified changes and no extra unplanned events. | scene 3 R4: The passage maintains consistent first‑person limited POV and past tense, matches the sample tone, and is a polished, narrative scene without any structural violations. | scene 3 R5: The prose aligns with canon and prior text, containing no contradictions and fulfills all planned beats. | scene 3 R2: not applicable: under two cast speakers with voice samples have attributed lines | scene 4 R1: All principal canon characters required for the scene (Aldous Kerr and Count Vasska) appear correctly and act as described, with no inappropriate invented protagonists. | scene 4 R3: The scene includes all five planned beats in the correct order with no unplanned events, fully matching the outline. | scene 4 R4: The passage maintains consistent Aldous POV and past tense, matches the dreamlike horror tone, and reads as publishable prose with only minor occasional phrasing issues. | scene 4 R5: The prose aligns with the established canon and prior text without contradictions, and no continuity errors are present. | scene 4 R2: not applicable: under two cast speakers with voice samples have attributed lines