Tracer
← polyphony · eval · frankenstein · ci

polyphony · claude-opus-5-5

✓ pass≠ not comparable
Pass rate
100%
Cases
1
Mode
eval
Suite
frankenstein
Env
ci
Started
2026-10-25 00:37 UTC
Duration
—
Cost
—
Tokens in/out
— / —
Commit
Branch
main
Source

Metrics

prose.score0.901 (was 0.691)
prose.words3,593 (was 3,565)

Labels

cadenceon-demand
experimentw16-r2-2
harness_sha6e14ad391bad41461cd8f8dc76e7871476724003
judge_providergroq
judge_self_gradedFalse
repeat1
triggerworkflow_dispatch

Compared with the previous run

Baseline 2026-10-24 09:49 UTC · 100% → this run 100% · code diff ↗

± score moved · 1
  • eval:prose: 0.69 → 0.90

Cases (1)

eval:prosescore 0.90✓ pass
score=0.901words=3,593queued=4deferred=0n_scenes=4r2_lines=15cast_named=1prose_chapter=1r2_applicable=0.500cast_from_beat=1r1_capped_scenes=0estimate_over_actual=0.562beat_seam_max_overlap=0scene_seam_max_overlap=0
Output
words=3593 path=planned rubrics={'R1': 1.0, 'R2': 0.21, 'R3': 1.0, 'R4': 1.0, 'R5': 1.0} seams=0/0
⚖︎ Judge rationale

scene 1 R1: All required canon characters (only Rowan Merrow) appear correctly with proper name and behavior, meeting the cast fidelity criteria fully. | scene 1 R3: The scene includes all five planned beats in correct order with no extraneous events, fully matching the outline. | scene 1 R4: The passage maintains consistent POV and tense, matches the restless exalted tone, and is a polished narrative without labels or repetition, meeting the 1.0 criteria. | scene 1 R5: The prose contains no contradictions to the established canon or prior scene and there are no planted errors to miss, meeting the rubric fully. | scene 1 R2: not applicable: under two cast speakers with voice samples have attributed lines | scene 2 R1: All required canon characters for the scene (Rowan Merrow) appear correctly with proper behavior, meeting the highest fidelity criteria. | scene 2 R3: All five planned beats appear in order, each change occurs, and no unplanned major events are added. | scene 2 R4: The passage maintains consistent POV and tense, matches the eerie awestruck tone, and is a polished narrative without prohibited elements. | scene 2 R5: The prose aligns with the canon and prior scene without contradictions, and no continuity errors are present. | scene 2 R2: not applicable: under two cast speakers with voice samples have attributed lines | scene 3 R1: All principal canon characters required for the scene (Rowan Merrow and Emeric Vandel) appear correctly with accurate names and behavior, and no unauthorized major characters are introduced. | scene 3 R2: No dialogue provided to assess voice distinctness, so cannot attribute lines, yielding a zero score. | scene 3 R3: The text realizes each planned beat in order, with the described changes, and adds no unplanned events. | scene 3 R4: The scene maintains consistent POV, tense, and tone, with varied concrete prose and no structural violations, meeting the highest rubric criteria. | scene 3 R5: The passage follows the canon and planned beats without contradictions, meeting continuity fully. | scene 4 R1: All required canon characters (Rowan Merrow and Emeric Vandel) appear, named correctly, and act in line with their canon descriptions. | scene 4 R2: Only about half of the untagged lines can be confidently matched to the correct character, with voices often generic and not fully reflecting the distinct diction of the samples. | scene 4 R3: All five planned beats appear in order, each with its required change, and no unplanned material is added. | scene 4 R4: The scene maintains consistent POV and tense, matches the intimate foreboding tone, and reads as polished narrative prose without structural errors. | scene 4 R5: The passage aligns with the established canon and prior scene, containing no contradictions and fulfilling the planned beats.