{"id":"W2958893609","doi":"10.1080/19439962.2018.1564946","title":"The big data analysis of rail equipment accidents based on the maximal information coefficient","year":2019,"lang":"en","type":"article","venue":"Journal of Transportation Safety & Security","topic":"Occupational Health and Safety Research","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Natural Science Foundation of China","keywords":"Accident (philosophy); Transport engineering; Engineering; Service (business); Fatal accident; Big data; Forensic engineering; Poison control; Computer security; Computer science; Business; Data mining; Environmental health","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006754245,0.0001204804,0.0003561426,0.0003140221,0.0006307673,0.0000169154,0.0007409201,0.0001035765,0.0005341289],"category_scores_gemma":[0.0003548879,0.00006639219,0.000207409,0.0009672907,0.0000588495,0.0003682258,0.00002502276,0.0007610418,0.00005893688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001695298,"about_ca_system_score_gemma":0.001158599,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001649811,"about_ca_topic_score_gemma":0.0006384452,"domain_scores_codex":[0.9954637,0.0006086858,0.001850116,0.0001302888,0.001620602,0.00032664],"domain_scores_gemma":[0.9936565,0.00300651,0.001462596,0.0006563167,0.001071219,0.0001468308],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.01683131,0.0006505314,0.8720807,0.0007439046,0.001206931,0.000005430149,0.01097783,0.04458629,0.00004563013,0.01071362,0.005256436,0.03690136],"study_design_scores_gemma":[0.001318751,0.0002036664,0.9362839,0.0001241111,0.000211556,1.952129e-7,0.001594449,0.03075814,0.00001145604,0.0001182582,0.02930831,0.0000671509],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.958866,0.0001435109,0.01395607,0.01896432,0.001976494,0.002060108,0.001997159,0.00001476601,0.002021587],"genre_scores_gemma":[0.9978666,0.0002231461,0.00006835569,0.0009657964,0.0000908989,0.00001142468,0.0007365177,0.00000639402,0.00003087458],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06420323,"threshold_uncertainty_score":0.5848336,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07995734244957357,"score_gpt":0.4144076548775141,"score_spread":0.3344503124279405,"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."}}