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

234 lines
4.7 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": 40,
"negatives": 200,
"unsourcedInP": 15
},
"arms": {
"staleness": {
"tp": 0,
"fp": 0,
"fn": 40,
"tn": 200,
"positives": 40,
"negatives": 200,
"flagged": 0,
"precision": null,
"recall": 0,
"f1": null,
"recallWilson": {
"p": 0,
"low": 0,
"high": 0.08762453925039232
},
"precisionWilson": null
},
"judge": {
"tp": 35,
"fp": 4,
"fn": 5,
"tn": 196,
"positives": 40,
"negatives": 200,
"flagged": 39,
"precision": 0.8974358974358975,
"recall": 0.875,
"f1": 0.8860759493670887,
"recallWilson": {
"p": 0.875,
"low": 0.7388757932976187,
"high": 0.9454058022645873
},
"precisionWilson": {
"p": 0.8974358974358975,
"low": 0.7642084129775517,
"high": 0.9593873444171301
}
},
"hybrid": {
"tp": 35,
"fp": 4,
"fn": 5,
"tn": 196,
"positives": 40,
"negatives": 200,
"flagged": 39,
"precision": 0.8974358974358975,
"recall": 0.875,
"f1": 0.8860759493670887,
"recallWilson": {
"p": 0.875,
"low": 0.7388757932976187,
"high": 0.9454058022645873
},
"precisionWilson": {
"p": 0.8974358974358975,
"low": 0.7642084129775517,
"high": 0.9593873444171301
}
}
},
"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": 1,
"fp": 1,
"fn": 0,
"tn": 13,
"positives": 1,
"negatives": 14,
"flagged": 2,
"precision": 0.5,
"recall": 1,
"f1": 0.6666666666666666,
"recallWilson": {
"p": 1,
"low": 0.2065432914738929,
"high": 1
},
"precisionWilson": {
"p": 0.5,
"low": 0.09452865480086614,
"high": 0.9054713451991339
}
},
"status": {
"tp": 6,
"fp": 3,
"fn": 2,
"tn": 42,
"positives": 8,
"negatives": 45,
"flagged": 9,
"precision": 0.6666666666666666,
"recall": 0.75,
"f1": 0.7058823529411765,
"recallWilson": {
"p": 0.75,
"low": 0.40926987910258916,
"high": 0.9285223111419724
},
"precisionWilson": {
"p": 0.6666666666666666,
"low": 0.3541973474990897,
"high": 0.8794184013172571
}
},
"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": 1,
"tn": 14,
"positives": 8,
"negatives": 14,
"flagged": 7,
"precision": 1,
"recall": 0.875,
"f1": 0.9333333333333333,
"recallWilson": {
"p": 0.875,
"low": 0.5291051942301386,
"high": 0.9775830911367038
},
"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"
]
}
}