{"id":"W3132719765","doi":"10.1155/2021/8819094","title":"Identifying and Labeling Potentially Risky Driving: A Multistage Process Using Real-World Driving Data","year":2021,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Traffic and Road Safety","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. Department of Transportation","keywords":"Process (computing); Computer science; Random forest; Logistic regression; Machine learning; Poison control; Artificial intelligence; Artificial neural network; Medicine; Medical emergency","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007646677,0.001071536,0.0009834691,0.002606236,0.001551046,0.001796373,0.001971508,0.001424118,0.0006609282],"category_scores_gemma":[0.01371884,0.0005807854,0.001957353,0.001947782,0.0007977324,0.001660221,0.002230786,0.002733936,0.0007264006],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001205225,"about_ca_system_score_gemma":0.002727477,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02675278,"about_ca_topic_score_gemma":0.05223181,"domain_scores_codex":[0.995463,0.001921288,0.0004053178,0.001032227,0.0008539329,0.0003242014],"domain_scores_gemma":[0.9908062,0.005228396,0.0007671744,0.0009666295,0.00194824,0.0002833523],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0008270523,0.002009301,0.3752497,0.0006788024,0.0004340887,0.0006428555,0.004598323,0.1136531,0.01731019,0.005233666,0.01138054,0.4679824],"study_design_scores_gemma":[0.00007333618,0.000428599,0.08065667,0.0001674062,0.0002129339,0.0003524023,0.002350598,0.8769144,0.0149686,0.01246873,0.01123844,0.0001678051],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.528045,0.0009082205,0.459121,0.001855175,0.0001156495,0.002539945,0.003830768,0.001390656,0.002193712],"genre_scores_gemma":[0.4459637,0.0002892448,0.5407464,0.0003148659,0.00006854122,0.0007380362,0.01016979,0.00007919771,0.001630252],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02675278,"threshold_uncertainty_score":0.05319411,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02324806933177206,"score_gpt":0.2967218223639271,"score_spread":0.2734737530321551,"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."}}