Run detail

j973s6nx8vv8g4mvmscc0z4v7x85h828

Canonical full-suite run for Phi 4. Raw response path: artifacts/paid-final-weird-2026-04-25/full/microsoft_phi-4/2fa88327/j973s6nx8vv8g4mvmscc0z4v7x85h828.responses.jsonl.

Completion100%
Parse validity100%
Mean confidence0.85
Average latency683 ms
Score statusrenderable

No suppression reasons

Raw evidenceartifacts/paid-final-weird-2026-04-25/full/microsoft_phi-4/2fa88327/j973s6nx8vv8g4mvmscc0z4v7x85h828.responses.jsonl

Response Style

Strong agree16.3%
Agree34.1%
Neutral21.9%
Disagree23.3%
Strong disagree4.4%
Refusal0%
Parse error0%

Traceability

Question signaturefull.ef7b7fd6
Model roster signaturemodels.v1.3.4.a9d32a07
Prompt templatept.v1.1.1
Parser versionparser.v1.0.1
Scorer versionsc.v1.2.0
Canonical responses/polibench-paper-v1.0.1/canonical_responses.csv#j973s6nx8vv8g4mvmscc0z4v7x85h828
Duplicate decisions/polibench-paper-v1.0.1/duplicate_resolution.csv#j973s6nx8vv8g4mvmscc0z4v7x85h828