verdict-coreml / verification-L128.json
alexwengg's picture
Bind Verdict parity reports to published Core ML package hashes
835208c verified
Raw History Blame Contribute Delete
6.4 kB
{
"source_repo": "heman10x/rlcd-modernbert-151m",
"source_revision": "8af2496eb63c7fa66d7d234e1f62629380030eb4",
"package": "verdict_fp16_L128_candidates25.mlpackage",
"package_files_sha256": {
"Data/com.apple.CoreML/model.mlmodel": "6cc079930a63c1069a7a2c259f4c086879981021047767f2bb4d68b6d1f02b00",
"Data/com.apple.CoreML/weights/weight.bin": "a982e14147982df9abb99a3637075a0193835c6b99edc396a52c1a43c2a4854a",
"Manifest.json": "fc5d31df174a9f450bfb9ba406307c379c30fabba5cad38fcaf8717b806c69a8"
},
"chip": "arm",
"macos": "27.0",
"max_calibrated_probability_error": 0.003407791923494219,
"selected_id_agreements": 4,
"questions": 4,
"rows": [
{
"name": "lost card",
"type": "choice",
"tokens": 53,
"candidates_including_abstention": 3,
"native": {
"type": "choice",
"selected_id": "card_lost",
"selected_probability": 0.627995456676331,
"probabilities": {
"card_lost": 0.627995456676331,
"pin_reset": 0.12699368118294335,
"__insufficient_evidence__": 0.2450108621407256
},
"concentration": 0.18185863532617996,
"is_abstention": false,
"p_abstain": 0.2450108621407256,
"calibration_status": "calibrated_for_scope",
"choice": "card_lost"
},
"coreml": {
"type": "choice",
"selected_id": "card_lost",
"selected_probability": 0.6283802556009165,
"probabilities": {
"card_lost": 0.6283802556009165,
"pin_reset": 0.1261597182435837,
"__insufficient_evidence__": 0.24546002615549983
},
"concentration": 0.18269014752444745,
"is_abstention": false,
"p_abstain": 0.24546002615549983,
"calibration_status": "calibrated_for_scope",
"choice": "card_lost"
},
"max_calibrated_probability_error": 0.0008339629393596393,
"selected_id_agrees": true,
"median_model_call_ms": 3.609708044677973
},
{
"name": "binary inquiry",
"type": "noul",
"tokens": 50,
"candidates_including_abstention": 3,
"native": {
"type": "noul",
"selected_id": "true",
"selected_probability": 0.46928461522757403,
"probabilities": {
"true": 0.46928461522757403,
"false": 0.24040802067067693,
"__insufficient_evidence__": 0.29030736410174907
},
"concentration": 0.03808313508410699,
"is_abstention": false,
"p_abstain": 0.29030736410174907,
"calibration_status": "calibrated_for_scope",
"noul": 0.6612505068952915,
"selected_outcome": "true"
},
"coreml": {
"type": "noul",
"selected_id": "true",
"selected_probability": 0.4658768233040798,
"probabilities": {
"true": 0.4658768233040798,
"false": 0.2409705632084786,
"__insufficient_evidence__": 0.29315261348744165
},
"concentration": 0.036521350138502884,
"is_abstention": false,
"p_abstain": 0.29315261348744165,
"calibration_status": "calibrated_for_scope",
"noul": 0.6590911025400003,
"selected_outcome": "true"
},
"max_calibrated_probability_error": 0.003407791923494219,
"selected_id_agrees": true,
"median_model_call_ms": 3.4036670112982392
},
{
"name": "urgency score",
"type": "score",
"tokens": 55,
"candidates_including_abstention": 4,
"native": {
"type": "score",
"selected_id": "__insufficient_evidence__",
"selected_probability": 0.3259147064757007,
"probabilities": {
"low": 0.1979320574725608,
"medium": 0.289823573347529,
"high": 0.18632966270420953,
"__insufficient_evidence__": 0.3259147064757007
},
"concentration": 0.02039159311536931,
"is_abstention": true,
"p_abstain": 0.3259147064757007,
"calibration_status": "calibrated_for_scope",
"score": null,
"selected_level_id": "__insufficient_evidence__",
"selected_value": null
},
"coreml": {
"type": "score",
"selected_id": "__insufficient_evidence__",
"selected_probability": 0.32674006867380345,
"probabilities": {
"low": 0.19782407464261623,
"medium": 0.2888377991986832,
"high": 0.18659805748489713,
"__insufficient_evidence__": 0.32674006867380345
},
"concentration": 0.020407770698545158,
"is_abstention": true,
"p_abstain": 0.32674006867380345,
"calibration_status": "calibrated_for_scope",
"score": null,
"selected_level_id": "__insufficient_evidence__",
"selected_value": null
},
"max_calibrated_probability_error": 0.0009857741488458194,
"selected_id_agrees": true,
"median_model_call_ms": 3.3971249940805137
},
{
"name": "insufficient evidence",
"type": "choice",
"tokens": 41,
"candidates_including_abstention": 3,
"native": {
"type": "choice",
"selected_id": "__insufficient_evidence__",
"selected_probability": 0.6003394036234859,
"probabilities": {
"visa": 0.19581438090218925,
"mastercard": 0.20384621547432477,
"__insufficient_evidence__": 0.6003394036234859
},
"concentration": 0.1354395684855455,
"is_abstention": true,
"p_abstain": 0.6003394036234859,
"calibration_status": "calibrated_for_scope",
"choice": "__insufficient_evidence__"
},
"coreml": {
"type": "choice",
"selected_id": "__insufficient_evidence__",
"selected_probability": 0.5997858326963917,
"probabilities": {
"visa": 0.19632166854967723,
"mastercard": 0.20389249875393106,
"__insufficient_evidence__": 0.5997858326963917
},
"concentration": 0.1348775837045153,
"is_abstention": true,
"p_abstain": 0.5997858326963917,
"calibration_status": "calibrated_for_scope",
"choice": "__insufficient_evidence__"
},
"max_calibrated_probability_error": 0.0005535709270941824,
"selected_id_agrees": true,
"median_model_call_ms": 3.4325000015087426
}
],
"passed": true
}