200 decisions · accuracy 100.0% · ECE 0.0036
cost $0.0037 · p50 0.863s · p99 7.494s
judge `jev` · model `typesafe-ai/jev` · backend `gateway` · recomputed 2026-09-19T09:09:12+00:00 (original run time not recorded) · judge-audit 0.2.0
Zero observed errors through the most confident 100.0%
(200 decisions, confidence ≥ 0.89).
Retrospective on this dataset — not a production guarantee.
| coverage | accuracy | min confidence | n |
|---|---|---|---|
| 5% | 100.0% | 1.00 | 10 |
| 15% | 100.0% | 1.00 | 30 |
| 25% | 100.0% | 1.00 | 50 |
| 35% | 100.0% | 1.00 | 70 |
| 45% | 100.0% | 1.00 | 90 |
| 55% | 100.0% | 1.00 | 110 |
| 65% | 100.0% | 1.00 | 130 |
| 75% | 100.0% | 1.00 | 150 |
| 85% | 100.0% | 1.00 | 170 |
| 95% | 100.0% | 0.98 | 190 |
| bin | avg confidence | accuracy | n |
|---|---|---|---|
| 0.8-0.9 | 0.890 | 100.0% | 2 |
| 0.9-1.0 | 0.998 | 100.0% | 198 |
A perfectly honest judge sits on the diagonal: avg confidence == accuracy in every bin.