{"id":"W4409633347","doi":"10.1088/3050-2454/adcef2","title":"Reliability engineering, risk management, and trustworthiness assurance for AI systems","year":2025,"lang":"en","type":"article","venue":"Journal of Reliability Science and Engineering","topic":"Risk and Safety Analysis","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Trustworthiness; Reliability engineering; Reliability (semiconductor); Risk management; Computer science; Quality assurance; Risk analysis (engineering); Engineering; Computer security; Operations management; Medicine; Business","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":[0.01625556,0.0001731725,0.0005224294,0.0007348838,0.0002737903,0.0004646822,0.0006789985,0.00007138418,0.000002251016],"category_scores_gemma":[0.0134716,0.0001227517,0.0001462753,0.002112775,0.0002286184,0.001093519,0.0001425448,0.000285328,7.999844e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001075232,"about_ca_system_score_gemma":0.0001281924,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002621006,"about_ca_topic_score_gemma":0.00000259917,"domain_scores_codex":[0.9970452,0.00004845268,0.001004954,0.0004818902,0.001095761,0.0003237804],"domain_scores_gemma":[0.9961314,0.001483088,0.0003203301,0.0005176063,0.001350373,0.0001972009],"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":[0.00009161389,0.00005704222,0.08984985,0.0004220612,0.00007431815,0.000006315448,0.0002741709,0.8696249,0.0004416568,0.005114587,0.001547728,0.03249579],"study_design_scores_gemma":[0.0005405279,0.00008039223,0.2489202,0.0001658653,0.0001115515,0.00001919384,0.0002926475,0.7017245,0.00008180274,0.00629265,0.04156714,0.0002035442],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7031702,0.001887285,0.2920312,0.001121433,0.001300811,0.0002891563,0.00001000074,0.00002555522,0.0001643756],"genre_scores_gemma":[0.9868237,0.001153632,0.01170827,0.00003557364,0.00006413362,0.000008661451,1.30725e-7,0.000005622803,0.0002003002],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2836535,"threshold_uncertainty_score":0.9948384,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01179522341916349,"score_gpt":0.2965353064739225,"score_spread":0.284740083054759,"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."}}