{"id":"W4407395040","doi":"10.1016/j.jsr.2025.02.007","title":"Visualizing what’s missing: Using deep learning and Bow-Tie diagrams to identify and visualize missing leading indicators in industrial construction","year":2025,"lang":"en","type":"article","venue":"Journal of Safety Research","topic":"Occupational Health and Safety Research","field":"Health Professions","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"PCL Construction (Canada); University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bow tie; Visualization; Data science; Missing data; Engineering; Computer science; Data mining; Artificial intelligence; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.01450001,0.0001926053,0.000611021,0.003800055,0.002369779,0.0002582392,0.0002291482,0.0004450327,0.00008511158],"category_scores_gemma":[0.006934837,0.0001820905,0.00006433182,0.002951646,0.0003287696,0.0009116983,0.0004009543,0.00428176,0.000008698987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001078423,"about_ca_system_score_gemma":0.002170562,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002138225,"about_ca_topic_score_gemma":0.00005770233,"domain_scores_codex":[0.9921442,0.003502273,0.001609876,0.0003775183,0.001249275,0.001116875],"domain_scores_gemma":[0.9927712,0.005146946,0.0004469481,0.0001383329,0.0007649622,0.0007316279],"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":[0.00177772,0.00006542166,0.4868586,0.000446949,0.00003929449,0.00004152601,0.003006285,0.00003485108,0.002153129,0.001020657,0.0001109062,0.5044446],"study_design_scores_gemma":[0.01496509,0.001929665,0.7205189,0.03221897,0.00009790544,0.0002369177,0.1252675,0.009969883,0.0007736075,0.006580901,0.08649957,0.0009410501],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9832931,0.004326125,0.00194739,0.007250164,0.001056776,0.001014806,0.00000243394,0.00001633779,0.001092885],"genre_scores_gemma":[0.9930128,0.003770915,0.002031984,0.0002115942,0.0006412318,0.00001586365,0.000004367111,0.00003475852,0.0002764897],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5035036,"threshold_uncertainty_score":0.998929,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2249819675563965,"score_gpt":0.5931228291484568,"score_spread":0.3681408615920603,"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."}}