{"id":"W2045765366","doi":"10.1115/icone17-75861","title":"Human Reliability, Experience and Error Probability: A New Benchmark","year":2009,"lang":"en","type":"article","venue":"Volume 2: Structural Integrity; Safety and Security; Advanced Applications of Nuclear Technology; Balance of Plant for Nuclear Applications","topic":"Risk and Safety Analysis","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Atomic Energy (Canada)","funders":"","keywords":"Benchmark (surveying); Reliability (semiconductor); Computer science; Human reliability; Reliability engineering; Human error; Simple (philosophy); Machine learning; Error analysis; Artificial intelligence; Data mining; Engineering; Mathematics; Power (physics)","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":[0.0005810098,0.000364081,0.0009231551,0.0004662565,0.0008588051,0.00008117356,0.001448147,0.0004289171,0.00013009],"category_scores_gemma":[0.0004501906,0.000320688,0.0002245798,0.00166091,0.001438887,0.0004562508,0.0002925842,0.0005810756,0.00001038892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006419979,"about_ca_system_score_gemma":0.00004749513,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009594989,"about_ca_topic_score_gemma":0.00005345751,"domain_scores_codex":[0.9963602,0.00005650858,0.001470865,0.001173929,0.0005241492,0.0004142986],"domain_scores_gemma":[0.9965045,0.0002555103,0.0008703902,0.001555764,0.0005946682,0.0002190987],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003520065,0.0002350929,0.001931713,0.00009645148,0.00006026688,4.243041e-7,0.001605165,0.000155111,0.01153498,0.7742195,0.001024603,0.2087847],"study_design_scores_gemma":[0.0006954385,0.0003617116,0.009828025,0.00004976305,0.00007320423,0.00003800419,0.002927867,0.006252324,0.0001939463,0.7974936,0.1816861,0.000400078],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9457148,0.001102057,0.01652198,0.02570708,0.00006401434,0.005828838,0.002936106,0.0005721732,0.001552927],"genre_scores_gemma":[0.9537218,0.0004931095,0.04526925,0.00009861757,0.0000388773,0.0001192461,0.0000892701,0.00002674807,0.0001430794],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2083846,"threshold_uncertainty_score":0.9999245,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01919908887390558,"score_gpt":0.3186369952895883,"score_spread":0.2994379064156827,"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."}}