{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009175476,0.000142294,0.0005282201,0.0001851298,0.0002362869,0.00004190241,0.0004940669,0.0002013328,0.00002854289],"category_scores_gemma":[0.01342187,0.00007949544,0.0003097688,0.0005359713,0.0006208515,0.0004768241,0.0001520396,0.0007331606,4.125882e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002308962,"about_ca_system_score_gemma":0.00006132662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002841552,"about_ca_topic_score_gemma":0.000006079044,"domain_scores_codex":[0.997019,0.00005172089,0.001439827,0.0002744826,0.001073183,0.0001417774],"domain_scores_gemma":[0.996516,0.000434114,0.001203166,0.0002470529,0.001422614,0.0001770061],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001406179,0.001761782,0.5675989,0.0005459252,0.0004011796,0.000002407731,0.003337196,0.01840531,0.1390695,0.1865126,0.005486181,0.07547279],"study_design_scores_gemma":[0.00287658,0.001298794,0.3110253,0.000391467,0.001035667,0.0001751508,0.002212413,0.02423334,0.05291854,0.5821456,0.02117691,0.0005102561],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.996647,0.0001068898,0.001206734,0.0009478683,0.0007121451,0.0001218137,0.00002256709,0.000007618775,0.000227366],"genre_scores_gemma":[0.9966325,0.0005933124,0.002620622,0.000008542313,0.0001181092,0.000001163232,2.470267e-7,0.000004028934,0.0000214325],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.395633,"threshold_uncertainty_score":0.9948885,"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."}}