{"id":"W3015586441","doi":"10.1016/bs.mcps.2020.03.001","title":"(mis)Using Bayesian networks for dynamic risk assessment","year":2020,"lang":"en","type":"book-chapter","venue":"Methods in chemical process safety","topic":"Risk and Safety Analysis","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Dynamic Bayesian network; Risk assessment; Computer science; Bayesian network; Reliability (semiconductor); Bayes' theorem; Bayesian probability; Machine learning; Metric (unit); Artificial intelligence; Dynamic assessment; Data mining; Risk analysis (engineering); Engineering; Computer security","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00906218,0.0007763908,0.002191583,0.0004133267,0.0002842368,0.0002080308,0.001927481,0.001135011,0.0005876325],"category_scores_gemma":[0.00490642,0.0006441471,0.001083631,0.0006897226,0.000304455,0.0002385596,0.0002651126,0.002041,0.00001458438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005298408,"about_ca_system_score_gemma":0.00039762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001404223,"about_ca_topic_score_gemma":0.00002203457,"domain_scores_codex":[0.9923618,0.0005414695,0.002760501,0.002096715,0.00158532,0.0006541806],"domain_scores_gemma":[0.9891796,0.007144061,0.001597712,0.001106641,0.000593563,0.0003784054],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005037859,0.00006562834,0.0001999738,0.0001467364,0.0002873345,0.00002190094,0.0002298589,0.03965484,0.0002419596,0.006410437,0.000344956,0.9518926],"study_design_scores_gemma":[0.0003803081,0.00002480726,0.00001215272,0.0001011812,0.0002368212,0.000003143721,0.000072294,0.5198166,0.00009221345,0.4616547,0.01710036,0.0005054311],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000004124435,0.0008740436,0.8431041,0.0008829117,0.0003030068,0.0005823268,0.000148909,0.00006431858,0.1540362],"genre_scores_gemma":[0.006144125,0.0007095883,0.9818193,0.0003487241,0.0005140154,0.00005367965,0.0001196945,0.0001506473,0.01014022],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9513872,"threshold_uncertainty_score":0.999601,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1114250090417366,"score_gpt":0.4961409751899047,"score_spread":0.3847159661481681,"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."}}