bench v2 prototype · label evidence_full-triggers · split selection · code 29933681bc47
corpus: 182 live records · triggers on 173 lessons (triggers.jsonl, sha 814c7bb5aa68) · queries sha 97ecbcb5d681 · nulls 550 (sha 6e100bad522c): 282 calibrate the line, 268 test it
score: evidence_full (The same over the lesson's whole text, body and fix included.)

alpha   line cap |           recall [95%] briefed/q | null test: briefed anything [95%]
 0.01 13.565   3 |   71.9% [65.5%, 78.3%]      1.35 | 4 of 268 (1.5%, [0.6%, 3.8%])
 0.01 13.565   5 |   71.9% [65.5%, 78.3%]      1.42 | 4 of 268 (1.5%, [0.6%, 3.8%])
 0.01 13.565   8 |   71.9% [65.5%, 78.3%]      1.43 | 4 of 268 (1.5%, [0.6%, 3.8%])
 0.05  8.250   3 |   83.9% [79.1%, 88.4%]      2.84 | 7 of 268 (2.6%, [1.3%, 5.3%])
 0.05  8.250   5 |   86.3% [81.9%, 90.4%]      4.26 | 7 of 268 (2.6%, [1.3%, 5.3%])
 0.05  8.250   8 |   87.6% [83.1%, 91.6%]      5.61 | 7 of 268 (2.6%, [1.3%, 5.3%])
  0.1  8.250   3 |   83.9% [79.1%, 88.4%]      2.84 | 7 of 268 (2.6%, [1.3%, 5.3%])
  0.1  8.250   5 |   86.3% [81.9%, 90.4%]      4.26 | 7 of 268 (2.6%, [1.3%, 5.3%])
  0.1  8.250   8 |   87.6% [83.1%, 91.6%]      5.61 | 7 of 268 (2.6%, [1.3%, 5.3%])

at alpha 0.05, cap 5, by register: bug-report 80/83 · paraphrase 65/83 · ticket 70/83
latency per decision: median 1.1 ms · p95 1.8 ms
