{"id":"W3209155894","doi":"10.1016/j.ssci.2021.105528","title":"Identification of human errors and influencing factors: A machine learning approach","year":2021,"lang":"en","type":"article","venue":"Safety Science","topic":"Occupational Health and Safety Research","field":"Health Professions","cited_by":46,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Engineering and Physical Sciences Research Council","keywords":"Human reliability; Computer science; Classifier (UML); Process (computing); Human error; Artificial intelligence; Reliability (semiconductor); Machine learning; Profiling (computer programming); Identification (biology); Human intelligence; Risk analysis (engineering); Knowledge management; Data science","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.002805613,0.00007410892,0.0001573614,0.0001544594,0.002155623,0.00001119501,0.000193297,0.00006280729,0.0000929572],"category_scores_gemma":[0.001578282,0.00006456764,0.00002259365,0.000960405,0.0003489532,0.0002949328,0.0002043056,0.0004840212,0.0000152842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001290034,"about_ca_system_score_gemma":0.001076495,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004536731,"about_ca_topic_score_gemma":0.00007893813,"domain_scores_codex":[0.9978282,0.0003139778,0.0005326242,0.0003295998,0.0005916081,0.0004039823],"domain_scores_gemma":[0.9985234,0.000361632,0.0002091653,0.000226363,0.000522508,0.0001568992],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003224196,0.00004184493,0.8923459,0.0004429625,0.000003369599,8.291455e-7,0.006502071,0.0001433546,0.08302967,0.01551267,0.00000576875,0.001939287],"study_design_scores_gemma":[0.0002534984,0.00003808931,0.9882743,0.00006506695,0.000002978406,0.000001224432,0.003416735,0.005504409,0.001478984,0.0006165539,0.0002755088,0.00007259552],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9924383,0.000165399,0.0007855768,0.0003444492,0.0001172519,0.0003110155,0.00001850096,0.0000269566,0.005792508],"genre_scores_gemma":[0.9989158,0.00004708135,0.0003386009,0.00005583819,0.0000319553,0.00001539032,0.00003317997,0.000006069731,0.0005560916],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09592843,"threshold_uncertainty_score":0.9991434,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08914070152563656,"score_gpt":0.4599645810235378,"score_spread":0.3708238794979012,"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."}}