# Benchmark run 20261015T171027Z-suite-crb_papers-naive-54c3f2

Status `success`, agent `naive`, commit `2925aeab2262`.

| suite | tasks | pass rate | 95% CI | incidents as fail | incident rate | tokens in / out | cost |
|---|---|---|---|---|---|---|---|
| crb_papers | 115 | 0.409 | [0.312, 0.509] (cluster_bootstrap) | 0.409 | 0.000 | 0 / 0 | — |

- crb_papers: pass rate excluding 1 gold defect(s) 0.412; tool coverage 79/120 (source_split); agent coverage 0/120 (source_split); failures out_of_tolerance 68

Rendered from summary.json; every number there is recomputable from results.jsonl.
