{"id":"W2908795312","doi":"10.1115/1.4042538","title":"Using Simulator Data to Facilitate Human Reliability Analysis","year":2019,"lang":"en","type":"article","venue":"Journal of Offshore Mechanics and Arctic Engineering","topic":"Risk and Safety Analysis","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"Lloyd's Register Foundation","keywords":"Computer science; Human reliability; Reliability (semiconductor); Prior probability; Bayesian network; Bayesian probability; Subject-matter expert; Domain (mathematical analysis); Machine learning; Human error; Set (abstract data type); Data mining; Data set; Reliability engineering; Simulation; Artificial intelligence; Engineering; Expert system","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":[0.004814423,0.0001486485,0.0006557347,0.0007484166,0.00008029763,0.0001609669,0.0008403652,0.00005738323,0.0001304919],"category_scores_gemma":[0.001558161,0.0001087482,0.0002637079,0.00148762,0.000006309948,0.0004357847,0.0003399598,0.0002362279,0.00001084412],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005369532,"about_ca_system_score_gemma":0.00003301553,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002856084,"about_ca_topic_score_gemma":0.00001122371,"domain_scores_codex":[0.9974044,0.0000673243,0.0009780278,0.0003730876,0.000963447,0.0002137253],"domain_scores_gemma":[0.9976081,0.0004707278,0.0003057921,0.0009577647,0.0004086624,0.0002490035],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001695211,0.00002145251,0.008070855,0.00001409028,0.000335568,0.000009436247,0.000272598,0.9851519,0.003860403,0.0006932184,0.00002861198,0.00152495],"study_design_scores_gemma":[0.0001732335,0.00009037979,0.004221409,0.00002945166,0.0004188113,0.00001269744,0.0003229545,0.9884194,0.00005773069,0.003646143,0.002459762,0.0001479901],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6533738,0.0001316997,0.3459446,0.0002762696,0.0001864542,0.00005623731,0.00001535984,0.000005133835,0.00001047877],"genre_scores_gemma":[0.9821993,0.00003846794,0.01758233,0.00003371292,0.00006248122,1.673793e-7,0.000002069959,0.000008914045,0.00007259927],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3288255,"threshold_uncertainty_score":0.4434622,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.193804592301393,"score_gpt":0.3682205905229774,"score_spread":0.1744159982215844,"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."}}