{"id":"W3082384432","doi":"10.1109/pmaps47429.2020.9183620","title":"Combining Historical Data and Domain Expert Knowledge Using Optimization to Model Electrical Equipment Reliability","year":2020,"lang":"en","type":"article","venue":"","topic":"Power System Reliability and Maintenance","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hydro-Québec","funders":"","keywords":"Reliability (semiconductor); Computer science; Reliability engineering; Asset (computer security); Domain (mathematical analysis); Data modeling; Asset management; Black box; Expert system; Engineering; Artificial intelligence; Software engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003500003,0.0001462229,0.0002465473,0.00003299527,0.00005730343,0.00002939329,0.0002564942,0.00007682778,0.00001149637],"category_scores_gemma":[0.000199115,0.0001387565,0.00002268775,0.0002260236,0.00001448858,0.0001895223,0.0002734712,0.0001242969,0.000006662027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005719635,"about_ca_system_score_gemma":0.00003794155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002409506,"about_ca_topic_score_gemma":0.000002929631,"domain_scores_codex":[0.998822,0.00004605456,0.0003292206,0.0004104333,0.0001322392,0.0002600446],"domain_scores_gemma":[0.9992057,0.00005821138,0.00001738934,0.0004130867,0.00003981544,0.0002657799],"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":[0.00002604163,0.00004579134,0.00005090127,0.00009343568,0.00001126896,0.000001659488,0.001923506,0.9835275,0.004120237,0.0003437095,0.00929218,0.0005637833],"study_design_scores_gemma":[0.0001983092,0.00004862614,0.000003122115,0.00002216604,0.000005709293,0.000003102782,0.00004548142,0.9903247,0.0001818743,0.00005699809,0.008935467,0.0001743956],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007365481,0.0005498304,0.9889637,0.0007098449,0.0001932749,0.0003335294,0.000005874263,0.0002409755,0.001637492],"genre_scores_gemma":[0.7601506,0.00002695968,0.2393117,0.0003263523,0.00007460442,0.0000246956,0.000009976558,0.00002860129,0.00004642186],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7527851,"threshold_uncertainty_score":0.5658324,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05719350354425663,"score_gpt":0.2709291005740166,"score_spread":0.21373559702976,"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."}}