FluidInference/verdict-coreml
042
1{2 "source_repo": "heman10x/rlcd-modernbert-151m",3 "source_revision": "8af2496eb63c7fa66d7d234e1f62629380030eb4",4 "package": "verdict_fp16_L512_candidates25.mlpackage",5 "package_files_sha256": {6 "Data/com.apple.CoreML/model.mlmodel": "7ad21a9ee93d1c573e6d89e6c35511f08c984a5c47108bb2b908c96344c03903",7 "Data/com.apple.CoreML/weights/weight.bin": "fb438de5823dd91c8448b373d026b7e6dcb7149bf871fde54057fd6d82586886",8 "Manifest.json": "047cc80f7d66d822ca0d9c0100a6a6dc96ae2d70eac42e292a2b246e01e64ddd"9 },10 "chip": "arm",11 "macos": "27.0",12 "max_calibrated_probability_error": 0.0006975581321209678,13 "selected_id_agreements": 5,14 "questions": 5,15 "rows": [16 {17 "name": "lost card",18 "type": "choice",19 "tokens": 53,20 "candidates_including_abstention": 3,21 "native": {22 "type": "choice",23 "selected_id": "card_lost",24 "selected_probability": 0.6279954438939314,25 "probabilities": {26 "card_lost": 0.6279954438939314,27 "pin_reset": 0.12699384187218735,28 "__insufficient_evidence__": 0.245010714233881329 },30 "concentration": 0.18185852825435922,31 "is_abstention": false,32 "p_abstain": 0.2450107142338813,33 "calibration_status": "calibrated_for_scope",34 "choice": "card_lost"35 },36 "coreml": {37 "type": "choice",38 "selected_id": "card_lost",39 "selected_probability": 0.6286024758124755,40 "probabilities": {41 "card_lost": 0.6286024758124755,42 "pin_reset": 0.12674703377209953,43 "__insufficient_evidence__": 0.2446504904154249744 },45 "concentration": 0.18252696123986079,46 "is_abstention": false,47 "p_abstain": 0.24465049041542497,48 "calibration_status": "calibrated_for_scope",49 "choice": "card_lost"50 },51 "max_calibrated_probability_error": 0.0006070319185441653,52 "selected_id_agrees": true,53 "median_model_call_ms": 8.42758401995524854 },55 {56 "name": "binary inquiry",57 "type": "noul",58 "tokens": 50,59 "candidates_including_abstention": 3,60 "native": {61 "type": "noul",62 "selected_id": "true",63 "selected_probability": 0.4692844463560151,64 "probabilities": {65 "true": 0.4692844463560151,66 "false": 0.24040823180168494,67 "__insufficient_evidence__": 0.2903073218422999668 },69 "concentration": 0.03808302501474403,70 "is_abstention": false,71 "p_abstain": 0.29030732184229996,72 "calibration_status": "calibrated_for_scope",73 "noul": 0.6612502295701238,74 "selected_outcome": "true"75 },76 "coreml": {77 "type": "noul",78 "selected_id": "true",79 "selected_probability": 0.46998200448813604,80 "probabilities": {81 "true": 0.46998200448813604,82 "false": 0.23993786932412314,83 "__insufficient_evidence__": 0.2900801261877407684 },85 "concentration": 0.03846968937399986,86 "is_abstention": false,87 "p_abstain": 0.29008012618774076,88 "calibration_status": "calibrated_for_scope",89 "noul": 0.6620211967927305,90 "selected_outcome": "true"91 },92 "max_calibrated_probability_error": 0.0006975581321209678,93 "selected_id_agrees": true,94 "median_model_call_ms": 8.43745900783687895 },96 {97 "name": "urgency score",98 "type": "score",99 "tokens": 55,100 "candidates_including_abstention": 4,101 "native": {102 "type": "score",103 "selected_id": "__insufficient_evidence__",104 "selected_probability": 0.3259148157325998,105 "probabilities": {106 "low": 0.19793214504236917,107 "medium": 0.2898236019444062,108 "high": 0.18632943728062487,109 "__insufficient_evidence__": 0.3259148157325998110 },111 "concentration": 0.02039165010923949,112 "is_abstention": true,113 "p_abstain": 0.3259148157325998,114 "calibration_status": "calibrated_for_scope",115 "score": null,116 "selected_level_id": "__insufficient_evidence__",117 "selected_value": null118 },119 "coreml": {120 "type": "score",121 "selected_id": "__insufficient_evidence__",122 "selected_probability": 0.3262236353210236,123 "probabilities": {124 "low": 0.19780841262370594,125 "medium": 0.28950115689828004,126 "high": 0.18646679515699038,127 "__insufficient_evidence__": 0.3262236353210236128 },129 "concentration": 0.020408360566200767,130 "is_abstention": true,131 "p_abstain": 0.3262236353210236,132 "calibration_status": "calibrated_for_scope",133 "score": null,134 "selected_level_id": "__insufficient_evidence__",135 "selected_value": null136 },137 "max_calibrated_probability_error": 0.000322445046126163,138 "selected_id_agrees": true,139 "median_model_call_ms": 8.381415973417461140 },141 {142 "name": "insufficient evidence",143 "type": "choice",144 "tokens": 41,145 "candidates_including_abstention": 3,146 "native": {147 "type": "choice",148 "selected_id": "__insufficient_evidence__",149 "selected_probability": 0.6003396635578521,150 "probabilities": {151 "visa": 0.19581437244279193,152 "mastercard": 0.2038459639993559,153 "__insufficient_evidence__": 0.6003396635578521154 },155 "concentration": 0.1354398243565177,156 "is_abstention": true,157 "p_abstain": 0.6003396635578521,158 "calibration_status": "calibrated_for_scope",159 "choice": "__insufficient_evidence__"160 },161 "coreml": {162 "type": "choice",163 "selected_id": "__insufficient_evidence__",164 "selected_probability": 0.6008594846026971,165 "probabilities": {166 "visa": 0.19567826624893642,167 "mastercard": 0.2034622491483665,168 "__insufficient_evidence__": 0.6008594846026971169 },170 "concentration": 0.13595645758378905,171 "is_abstention": true,172 "p_abstain": 0.6008594846026971,173 "calibration_status": "calibrated_for_scope",174 "choice": "__insufficient_evidence__"175 },176 "max_calibrated_probability_error": 0.000519821044845048,177 "selected_id_agrees": true,178 "median_model_call_ms": 8.738874981645495179 },180 {181 "name": "BFCL-tool-selection:simple:simple_254",182 "type": "choice",183 "tokens": 283,184 "candidates_including_abstention": 3,185 "native": {186 "type": "choice",187 "selected_id": "yes",188 "selected_probability": 0.5095718104586857,189 "probabilities": {190 "yes": 0.5095718104586857,191 "no": 0.28447377613128705,192 "__insufficient_evidence__": 0.20595441341002724193 },194 "concentration": 0.0655574261710149,195 "is_abstention": false,196 "p_abstain": 0.20595441341002724,197 "calibration_status": "calibrated_for_scope",198 "choice": "yes"199 },200 "coreml": {201 "type": "choice",202 "selected_id": "yes",203 "selected_probability": 0.5093345700124705,204 "probabilities": {205 "yes": 0.5093345700124705,206 "no": 0.28465867339056805,207 "__insufficient_evidence__": 0.20600675659696147208 },209 "concentration": 0.06541626747983909,210 "is_abstention": false,211 "p_abstain": 0.20600675659696147,212 "calibration_status": "calibrated_for_scope",213 "choice": "yes"214 },215 "max_calibrated_probability_error": 0.00023724044621520335,216 "selected_id_agrees": true,217 "median_model_call_ms": 10.042167035862803218 }219 ],220 "passed": true221}222 