{"id":"W2155116765","doi":"10.3141/1784-08","title":"Calibration and Transferability of Accident Prediction Models for Urban Intersections","year":2002,"lang":"en","type":"article","venue":"Transportation Research Record Journal of the Transportation Research Board","topic":"Traffic and Road Safety","field":"Engineering","cited_by":138,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Transferability; Calibration; Computer science; Transport engineering; Traffic volume; Engineering; Statistics; Machine learning; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001801546,0.0001670952,0.0003345582,0.0005625218,0.0003241454,0.00004541655,0.0003505135,0.0001662437,0.0001101436],"category_scores_gemma":[0.00004822326,0.0001328471,0.0002780879,0.000837405,0.0003518163,0.0007637571,0.000002111565,0.000983199,8.490478e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001364217,"about_ca_system_score_gemma":0.00007436225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007081364,"about_ca_topic_score_gemma":0.009008802,"domain_scores_codex":[0.9965762,0.0003226232,0.001141936,0.0002303137,0.001296752,0.0004321889],"domain_scores_gemma":[0.9975228,0.0005483195,0.0001256439,0.0002523072,0.001338284,0.0002126727],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.002710141,0.0009686747,0.4204092,0.002455892,0.0009028375,0.00002023628,0.03880644,0.4456332,0.01181391,0.01121073,0.02816342,0.03690528],"study_design_scores_gemma":[0.002493689,0.0009733763,0.8357508,0.0003609988,0.0001161813,0.000001058316,0.00268155,0.14696,0.003319335,0.004555855,0.002562054,0.0002250362],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9222049,0.0004218346,0.07476073,0.0008071113,0.0004646751,0.001016933,0.0001686923,0.00004961283,0.0001055875],"genre_scores_gemma":[0.996766,0.001816119,0.001031724,0.000006139524,0.0001209513,0.00007929508,0.00001530748,0.00003906453,0.0001254359],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4153416,"threshold_uncertainty_score":0.5417345,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08624799702785202,"score_gpt":0.3201905006857133,"score_spread":0.2339425036578612,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}