{"id":"W1977543843","doi":"10.1243/1748006xjrr307","title":"Human reliability: Benchmark and prediction","year":2010,"lang":"en","type":"article","venue":"Proceedings of the Institution of Mechanical Engineers Part O Journal of Risk and Reliability","topic":"Risk and Safety Analysis","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Atomic Energy (Canada)","funders":"","keywords":"Human reliability; Computer science; Benchmark (surveying); Reliability (semiconductor); Human error; Reliability engineering; Machine learning; Risk assessment; Artificial intelligence; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008039611,0.000925358,0.0007592881,0.002914442,0.0003019483,0.001297856,0.001402128,0.001108359,0.00104417],"category_scores_gemma":[0.02960901,0.0001818181,0.000535883,0.001516815,0.0008778835,0.001200642,0.001214213,0.0009024462,0.0004067074],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008562604,"about_ca_system_score_gemma":0.0007871497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00275698,"about_ca_topic_score_gemma":0.001696397,"domain_scores_codex":[0.9919687,0.002692547,0.0003787652,0.0007498837,0.003983409,0.0002267345],"domain_scores_gemma":[0.9852246,0.006601392,0.001413483,0.003215466,0.003269546,0.0002755265],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006589191,0.000618523,0.03899115,0.0007312489,0.0002562816,0.0002129414,0.000535238,0.476141,0.01383124,0.0178425,0.007669081,0.4425119],"study_design_scores_gemma":[0.00004103892,0.001661201,0.04384965,0.0001792983,0.00005721457,0.0003601944,0.0002062739,0.9145899,0.01881179,0.01413271,0.005994692,0.0001160243],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3424068,0.003689326,0.6284716,0.0006270182,0.0003535235,0.0004417148,0.001755494,0.002210756,0.02004368],"genre_scores_gemma":[0.9203083,0.0006732341,0.07561435,0.00006232761,0.0001079468,0.0002529833,0.001301475,0.0001043202,0.001575147],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008039611,"threshold_uncertainty_score":0.04251802,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01487606807846977,"score_gpt":0.2748612125558909,"score_spread":0.2599851444774211,"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."}}