ms-ai-architect/scripts/kb-eval/data/judge-bakeoff-report-v3-g5bgold.json

234 lines
4.5 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": 39,
"fp": 0,
"fn": 3,
"tn": 198,
"positives": 42,
"negatives": 198,
"flagged": 39,
"precision": 1,
"recall": 0.9285714285714286,
"f1": 0.962962962962963,
"recallWilson": {
"p": 0.9285714285714286,
"low": 0.8099028671147483,
"high": 0.9754100364488272
},
"precisionWilson": {
"p": 1,
"low": 0.9103301463997611,
"high": 1
}
},
"hybrid": {
"tp": 39,
"fp": 0,
"fn": 3,
"tn": 198,
"positives": 42,
"negatives": 198,
"flagged": 39,
"precision": 1,
"recall": 0.9285714285714286,
"f1": 0.962962962962963,
"recallWilson": {
"p": 0.9285714285714286,
"low": 0.8099028671147483,
"high": 0.9754100364488272
},
"precisionWilson": {
"p": 1,
"low": 0.9103301463997611,
"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": 9,
"fp": 0,
"fn": 1,
"tn": 43,
"positives": 10,
"negatives": 43,
"flagged": 9,
"precision": 1,
"recall": 0.9,
"f1": 0.9473684210526316,
"recallWilson": {
"p": 0.9,
"low": 0.5958436145024278,
"high": 0.9821242504842788
},
"precisionWilson": {
"p": 1,
"low": 0.7008472464490407,
"high": 1
}
},
"taxonomy": {
"tp": 9,
"fp": 0,
"fn": 2,
"tn": 86,
"positives": 11,
"negatives": 86,
"flagged": 9,
"precision": 1,
"recall": 0.8181818181818182,
"f1": 0.9,
"recallWilson": {
"p": 0.8181818181818182,
"low": 0.5230138624217553,
"high": 0.9486333993289995
},
"precisionWilson": {
"p": 1,
"low": 0.7008472464490407,
"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"
]
}
}