Kjell Tore Guttormsen
09bc99eec8
45-veis v3.1 fan-out kjørt per runbook: 255 claims / 45 filer, 45 Opus-4.8-xhigh- subagenter (live MS Learn, blinde for gull, én per fil), aggregert 255/255 rent → deterministisk re-score mot G5b-korrigert gull. Resultat: v3.1 = P 100,0 / R 100,0 / 0 FP / 0 FN / F1 1,000 (TP 42, TN 198) mot v3-baren P 100,0 / R 92,9 / 3 FN. Alle 3 gjenstående FN fanget (R1 øvre-grense, R7 last-bærende-streng, R8 fler-delt) UTEN én ny FP. Forhåndsregistrert gate (hold P=100 ∧ løft R>92,9) klarert → v3.1 ADOPTERT som judge. R1-«+»-floor-flagg over full populasjon avkreftet som FP-risiko: alle matchet gull (decision-changing floors = outdated/TP; tette floors = correct/TN). §8 G1 lukket, G2 avblokkert (v3.1 = prompt å wire i transform.mjs). Suite 641/641. [skip-docs]
234 lines
4.3 KiB
JSON
234 lines
4.3 KiB
JSON
{
|
|
"_meta": {
|
|
"source": "gold-correctness-set.json + judge-bakeoff-results.json",
|
|
"thresholds": {
|
|
"minRecall": 0.7,
|
|
"minPrecision": 0.6
|
|
},
|
|
"judged": 255
|
|
},
|
|
"population": {
|
|
"total": 255,
|
|
"verifiable": 240,
|
|
"positives": 42,
|
|
"negatives": 198,
|
|
"unsourcedInP": 15
|
|
},
|
|
"arms": {
|
|
"staleness": {
|
|
"tp": 0,
|
|
"fp": 0,
|
|
"fn": 42,
|
|
"tn": 198,
|
|
"positives": 42,
|
|
"negatives": 198,
|
|
"flagged": 0,
|
|
"precision": null,
|
|
"recall": 0,
|
|
"f1": null,
|
|
"recallWilson": {
|
|
"p": 0,
|
|
"low": 0,
|
|
"high": 0.08380161250916199
|
|
},
|
|
"precisionWilson": null
|
|
},
|
|
"judge": {
|
|
"tp": 42,
|
|
"fp": 0,
|
|
"fn": 0,
|
|
"tn": 198,
|
|
"positives": 42,
|
|
"negatives": 198,
|
|
"flagged": 42,
|
|
"precision": 1,
|
|
"recall": 1,
|
|
"f1": 1,
|
|
"recallWilson": {
|
|
"p": 1,
|
|
"low": 0.9161983874908382,
|
|
"high": 1
|
|
},
|
|
"precisionWilson": {
|
|
"p": 1,
|
|
"low": 0.9161983874908382,
|
|
"high": 1
|
|
}
|
|
},
|
|
"hybrid": {
|
|
"tp": 42,
|
|
"fp": 0,
|
|
"fn": 0,
|
|
"tn": 198,
|
|
"positives": 42,
|
|
"negatives": 198,
|
|
"flagged": 42,
|
|
"precision": 1,
|
|
"recall": 1,
|
|
"f1": 1,
|
|
"recallWilson": {
|
|
"p": 1,
|
|
"low": 0.9161983874908382,
|
|
"high": 1
|
|
},
|
|
"precisionWilson": {
|
|
"p": 1,
|
|
"low": 0.9161983874908382,
|
|
"high": 1
|
|
}
|
|
}
|
|
},
|
|
"sourceSilent": {
|
|
"onVerifiableNegative": 0,
|
|
"onVerifiableError": 0,
|
|
"agreesWithUnsourced": 2,
|
|
"disagreesWithUnsourced": 13
|
|
},
|
|
"byClaimType": {
|
|
"version": {
|
|
"tp": 7,
|
|
"fp": 0,
|
|
"fn": 0,
|
|
"tn": 21,
|
|
"positives": 7,
|
|
"negatives": 21,
|
|
"flagged": 7,
|
|
"precision": 1,
|
|
"recall": 1,
|
|
"f1": 1,
|
|
"recallWilson": {
|
|
"p": 1,
|
|
"low": 0.6456611570247934,
|
|
"high": 1
|
|
},
|
|
"precisionWilson": {
|
|
"p": 1,
|
|
"low": 0.6456611570247934,
|
|
"high": 1
|
|
}
|
|
},
|
|
"tpm": {
|
|
"tp": 5,
|
|
"fp": 0,
|
|
"fn": 0,
|
|
"tn": 20,
|
|
"positives": 5,
|
|
"negatives": 20,
|
|
"flagged": 5,
|
|
"precision": 1,
|
|
"recall": 1,
|
|
"f1": 1,
|
|
"recallWilson": {
|
|
"p": 1,
|
|
"low": 0.5655085052479191,
|
|
"high": 1
|
|
},
|
|
"precisionWilson": {
|
|
"p": 1,
|
|
"low": 0.5655085052479191,
|
|
"high": 1
|
|
}
|
|
},
|
|
"region": {
|
|
"tp": 2,
|
|
"fp": 0,
|
|
"fn": 0,
|
|
"tn": 13,
|
|
"positives": 2,
|
|
"negatives": 13,
|
|
"flagged": 2,
|
|
"precision": 1,
|
|
"recall": 1,
|
|
"f1": 1,
|
|
"recallWilson": {
|
|
"p": 1,
|
|
"low": 0.34237195288961925,
|
|
"high": 1
|
|
},
|
|
"precisionWilson": {
|
|
"p": 1,
|
|
"low": 0.34237195288961925,
|
|
"high": 1
|
|
}
|
|
},
|
|
"status": {
|
|
"tp": 10,
|
|
"fp": 0,
|
|
"fn": 0,
|
|
"tn": 43,
|
|
"positives": 10,
|
|
"negatives": 43,
|
|
"flagged": 10,
|
|
"precision": 1,
|
|
"recall": 1,
|
|
"f1": 1,
|
|
"recallWilson": {
|
|
"p": 1,
|
|
"low": 0.7224598312333834,
|
|
"high": 1
|
|
},
|
|
"precisionWilson": {
|
|
"p": 1,
|
|
"low": 0.7224598312333834,
|
|
"high": 1
|
|
}
|
|
},
|
|
"taxonomy": {
|
|
"tp": 11,
|
|
"fp": 0,
|
|
"fn": 0,
|
|
"tn": 86,
|
|
"positives": 11,
|
|
"negatives": 86,
|
|
"flagged": 11,
|
|
"precision": 1,
|
|
"recall": 1,
|
|
"f1": 1,
|
|
"recallWilson": {
|
|
"p": 1,
|
|
"low": 0.7411599827511859,
|
|
"high": 1
|
|
},
|
|
"precisionWilson": {
|
|
"p": 1,
|
|
"low": 0.7411599827511859,
|
|
"high": 1
|
|
}
|
|
},
|
|
"sku": {
|
|
"tp": 7,
|
|
"fp": 0,
|
|
"fn": 0,
|
|
"tn": 15,
|
|
"positives": 7,
|
|
"negatives": 15,
|
|
"flagged": 7,
|
|
"precision": 1,
|
|
"recall": 1,
|
|
"f1": 1,
|
|
"recallWilson": {
|
|
"p": 1,
|
|
"low": 0.6456611570247934,
|
|
"high": 1
|
|
},
|
|
"precisionWilson": {
|
|
"p": 1,
|
|
"low": 0.6456611570247934,
|
|
"high": 1
|
|
}
|
|
}
|
|
},
|
|
"gate": {
|
|
"pass": true,
|
|
"recallOk": true,
|
|
"precisionOk": true,
|
|
"beatsStaleness": true,
|
|
"thresholds": {
|
|
"minRecall": 0.7,
|
|
"minPrecision": 0.6
|
|
},
|
|
"reasons": [
|
|
"all criteria met"
|
|
]
|
|
}
|
|
}
|