ms-ai-architect/scripts/kb-eval/data/judge-bakeoff-report-v2-g5bgold.json

234 lines
4.9 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": 33,
"fp": 5,
"fn": 9,
"tn": 193,
"positives": 42,
"negatives": 198,
"flagged": 38,
"precision": 0.868421052631579,
"recall": 0.7857142857142857,
"f1": 0.825,
"recallWilson": {
"p": 0.7857142857142857,
"low": 0.6405986210195627,
"high": 0.8829433146894876
},
"precisionWilson": {
"p": 0.868421052631579,
"low": 0.7267282994850112,
"high": 0.9424621712426856
}
},
"hybrid": {
"tp": 33,
"fp": 5,
"fn": 9,
"tn": 193,
"positives": 42,
"negatives": 198,
"flagged": 38,
"precision": 0.868421052631579,
"recall": 0.7857142857142857,
"f1": 0.825,
"recallWilson": {
"p": 0.7857142857142857,
"low": 0.6405986210195627,
"high": 0.8829433146894876
},
"precisionWilson": {
"p": 0.868421052631579,
"low": 0.7267282994850112,
"high": 0.9424621712426856
}
}
},
"sourceSilent": {
"onVerifiableNegative": 1,
"onVerifiableError": 4,
"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": 4,
"tn": 42,
"positives": 10,
"negatives": 43,
"flagged": 7,
"precision": 0.8571428571428571,
"recall": 0.6,
"f1": 0.7058823529411764,
"recallWilson": {
"p": 0.6,
"low": 0.3126695474501863,
"high": 0.8318224187964902
},
"precisionWilson": {
"p": 0.8571428571428571,
"low": 0.4868654966809701,
"high": 0.9743210440510252
}
},
"taxonomy": {
"tp": 11,
"fp": 3,
"fn": 0,
"tn": 83,
"positives": 11,
"negatives": 86,
"flagged": 14,
"precision": 0.7857142857142857,
"recall": 1,
"f1": 0.88,
"recallWilson": {
"p": 1,
"low": 0.7411599827511859,
"high": 1
},
"precisionWilson": {
"p": 0.7857142857142857,
"low": 0.5241027622679172,
"high": 0.9242875166308363
}
},
"sku": {
"tp": 5,
"fp": 1,
"fn": 2,
"tn": 14,
"positives": 7,
"negatives": 15,
"flagged": 6,
"precision": 0.8333333333333334,
"recall": 0.7142857142857143,
"f1": 0.7692307692307692,
"recallWilson": {
"p": 0.7142857142857143,
"low": 0.35892909014821267,
"high": 0.9177828342909844
},
"precisionWilson": {
"p": 0.8333333333333334,
"low": 0.43649056343635395,
"high": 0.9699474141282697
}
}
},
"gate": {
"pass": true,
"recallOk": true,
"precisionOk": true,
"beatsStaleness": true,
"thresholds": {
"minRecall": 0.7,
"minPrecision": 0.6
},
"reasons": [
"all criteria met"
]
}
}