Operatørvalg (c): én målrettet, prinsipiell prompt-iterasjon på den diagnostiserte grounded-men-feil-feilmoden (eksakt-verdi-entailment). Terskel uendret; v1 frosset. Full blind v2 fan-out (15 batcher Opus 4.8 xhigh, 255 P-påstander dekket): - judge v2: recall 84.2% (32/38, PASS >=0.80, Wilson [69.6-92.6%]), presisjon 84.2% (PASS >=0.70), F1 0.842, slår staleness 0/38. - Fiksen løste målet: sku recall 37.5%->75.0%, taxonomy 66.7%->100%. - +6 ekte fangster (26->32) uten netto nye FP (6->6) => recall OG presisjon opp. Forbehold (ærlig): andre måling på samme frosne sett etter v1 (erkjent); Wilson nedre grense 69.6% < 0.80 ved n=38; én iterasjon. Gate-logikk => vei mot S3. Stoppet for operatør-beslutning (S2/S3), eskalerer ikke selv. run-judge-bakeoff.mjs: --results/--report-prefix flagg (v2 uten å klobbe v1). Suite 552/552.
234 lines
4.9 KiB
JSON
234 lines
4.9 KiB
JSON
{
|
|
"_meta": {
|
|
"source": "gold-correctness-set.json + judge-bakeoff-results.json",
|
|
"thresholds": {
|
|
"minRecall": 0.8,
|
|
"minPrecision": 0.7
|
|
},
|
|
"judged": 255
|
|
},
|
|
"population": {
|
|
"total": 255,
|
|
"verifiable": 240,
|
|
"positives": 38,
|
|
"negatives": 202,
|
|
"unsourcedInP": 15
|
|
},
|
|
"arms": {
|
|
"staleness": {
|
|
"tp": 0,
|
|
"fp": 0,
|
|
"fn": 38,
|
|
"tn": 202,
|
|
"positives": 38,
|
|
"negatives": 202,
|
|
"flagged": 0,
|
|
"precision": null,
|
|
"recall": 0,
|
|
"f1": null,
|
|
"recallWilson": {
|
|
"p": 0,
|
|
"low": 0,
|
|
"high": 0.09181293258383999
|
|
},
|
|
"precisionWilson": null
|
|
},
|
|
"judge": {
|
|
"tp": 32,
|
|
"fp": 6,
|
|
"fn": 6,
|
|
"tn": 196,
|
|
"positives": 38,
|
|
"negatives": 202,
|
|
"flagged": 38,
|
|
"precision": 0.8421052631578947,
|
|
"recall": 0.8421052631578947,
|
|
"f1": 0.8421052631578947,
|
|
"recallWilson": {
|
|
"p": 0.8421052631578947,
|
|
"low": 0.6958287736272311,
|
|
"high": 0.9255623777627731
|
|
},
|
|
"precisionWilson": {
|
|
"p": 0.8421052631578947,
|
|
"low": 0.6958287736272311,
|
|
"high": 0.9255623777627731
|
|
}
|
|
},
|
|
"hybrid": {
|
|
"tp": 32,
|
|
"fp": 6,
|
|
"fn": 6,
|
|
"tn": 196,
|
|
"positives": 38,
|
|
"negatives": 202,
|
|
"flagged": 38,
|
|
"precision": 0.8421052631578947,
|
|
"recall": 0.8421052631578947,
|
|
"f1": 0.8421052631578947,
|
|
"recallWilson": {
|
|
"p": 0.8421052631578947,
|
|
"low": 0.6958287736272311,
|
|
"high": 0.9255623777627731
|
|
},
|
|
"precisionWilson": {
|
|
"p": 0.8421052631578947,
|
|
"low": 0.6958287736272311,
|
|
"high": 0.9255623777627731
|
|
}
|
|
}
|
|
},
|
|
"sourceSilent": {
|
|
"onVerifiableNegative": 3,
|
|
"onVerifiableError": 2,
|
|
"agreesWithUnsourced": 5,
|
|
"disagreesWithUnsourced": 10
|
|
},
|
|
"byClaimType": {
|
|
"version": {
|
|
"tp": 6,
|
|
"fp": 0,
|
|
"fn": 1,
|
|
"tn": 21,
|
|
"positives": 7,
|
|
"negatives": 21,
|
|
"flagged": 6,
|
|
"precision": 1,
|
|
"recall": 0.8571428571428571,
|
|
"f1": 0.923076923076923,
|
|
"recallWilson": {
|
|
"p": 0.8571428571428571,
|
|
"low": 0.4868654966809701,
|
|
"high": 0.9743210440510252
|
|
},
|
|
"precisionWilson": {
|
|
"p": 1,
|
|
"low": 0.6096569663469354,
|
|
"high": 0.9999999999999999
|
|
}
|
|
},
|
|
"tpm": {
|
|
"tp": 4,
|
|
"fp": 0,
|
|
"fn": 1,
|
|
"tn": 20,
|
|
"positives": 5,
|
|
"negatives": 20,
|
|
"flagged": 4,
|
|
"precision": 1,
|
|
"recall": 0.8,
|
|
"f1": 0.888888888888889,
|
|
"recallWilson": {
|
|
"p": 0.8,
|
|
"low": 0.3755282641185388,
|
|
"high": 0.9637768390302125
|
|
},
|
|
"precisionWilson": {
|
|
"p": 1,
|
|
"low": 0.5100999795960008,
|
|
"high": 1
|
|
}
|
|
},
|
|
"region": {
|
|
"tp": 1,
|
|
"fp": 0,
|
|
"fn": 1,
|
|
"tn": 13,
|
|
"positives": 2,
|
|
"negatives": 13,
|
|
"flagged": 1,
|
|
"precision": 1,
|
|
"recall": 0.5,
|
|
"f1": 0.6666666666666666,
|
|
"recallWilson": {
|
|
"p": 0.5,
|
|
"low": 0.09452865480086614,
|
|
"high": 0.9054713451991339
|
|
},
|
|
"precisionWilson": {
|
|
"p": 1,
|
|
"low": 0.2065432914738929,
|
|
"high": 1
|
|
}
|
|
},
|
|
"status": {
|
|
"tp": 6,
|
|
"fp": 1,
|
|
"fn": 1,
|
|
"tn": 45,
|
|
"positives": 7,
|
|
"negatives": 46,
|
|
"flagged": 7,
|
|
"precision": 0.8571428571428571,
|
|
"recall": 0.8571428571428571,
|
|
"f1": 0.8571428571428571,
|
|
"recallWilson": {
|
|
"p": 0.8571428571428571,
|
|
"low": 0.4868654966809701,
|
|
"high": 0.9743210440510252
|
|
},
|
|
"precisionWilson": {
|
|
"p": 0.8571428571428571,
|
|
"low": 0.4868654966809701,
|
|
"high": 0.9743210440510252
|
|
}
|
|
},
|
|
"taxonomy": {
|
|
"tp": 9,
|
|
"fp": 5,
|
|
"fn": 0,
|
|
"tn": 83,
|
|
"positives": 9,
|
|
"negatives": 88,
|
|
"flagged": 14,
|
|
"precision": 0.6428571428571429,
|
|
"recall": 1,
|
|
"f1": 0.782608695652174,
|
|
"recallWilson": {
|
|
"p": 1,
|
|
"low": 0.7008472464490407,
|
|
"high": 1
|
|
},
|
|
"precisionWilson": {
|
|
"p": 0.6428571428571429,
|
|
"low": 0.3876400468214041,
|
|
"high": 0.8365550926279728
|
|
}
|
|
},
|
|
"sku": {
|
|
"tp": 6,
|
|
"fp": 0,
|
|
"fn": 2,
|
|
"tn": 14,
|
|
"positives": 8,
|
|
"negatives": 14,
|
|
"flagged": 6,
|
|
"precision": 1,
|
|
"recall": 0.75,
|
|
"f1": 0.8571428571428571,
|
|
"recallWilson": {
|
|
"p": 0.75,
|
|
"low": 0.40926987910258916,
|
|
"high": 0.9285223111419724
|
|
},
|
|
"precisionWilson": {
|
|
"p": 1,
|
|
"low": 0.6096569663469354,
|
|
"high": 0.9999999999999999
|
|
}
|
|
}
|
|
},
|
|
"gate": {
|
|
"pass": true,
|
|
"recallOk": true,
|
|
"precisionOk": true,
|
|
"beatsStaleness": true,
|
|
"thresholds": {
|
|
"minRecall": 0.8,
|
|
"minPrecision": 0.7
|
|
},
|
|
"reasons": [
|
|
"all criteria met"
|
|
]
|
|
}
|
|
}
|