{"id":"W2002105260","doi":"10.1109/epec.2012.6474933","title":"Towards cost-effective maintenance of power transformer by accurately predicting its insulation condition","year":2012,"lang":"en","type":"article","venue":"","topic":"Power Transformer Diagnostics and Insulation","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Transformer; Dissolved gas analysis; Transformer oil; Partial discharge; Voltage; Artificial neural network; Electrical engineering; Computer science; Automotive engineering; Environmental science; Process engineering; Engineering; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.0001643128,0.0001440162,0.0001531175,0.00006896648,0.00003581267,0.00001274517,0.00005388288,0.0001008315,0.000196592],"category_scores_gemma":[0.00004043442,0.0001332229,0.0000529324,0.0001655778,0.00001997118,0.0008426537,0.000002648548,0.0001089155,0.00002339188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000077025,"about_ca_system_score_gemma":0.00000861579,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001425036,"about_ca_topic_score_gemma":0.000002093246,"domain_scores_codex":[0.9991519,0.00001501233,0.0002819055,0.00009429718,0.0001638754,0.0002930206],"domain_scores_gemma":[0.9996369,0.00007039428,0.00003854043,0.0000769859,0.00009304656,0.0000841131],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001592333,0.0005852257,0.03473127,0.0006673909,0.0005031695,0.000001325677,0.008160062,0.01577961,0.7555719,0.02497375,0.006807107,0.15206],"study_design_scores_gemma":[0.001315573,0.0001507302,0.3421125,0.0001223297,0.00005865481,0.000005146784,0.0001938639,0.03953565,0.6016349,0.0001881295,0.0142809,0.0004016893],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7544581,0.0005175265,0.1948014,0.00004451025,0.0006357819,0.001262374,0.0002240415,0.0001989265,0.04785735],"genre_scores_gemma":[0.999327,0.0001597515,0.0001335548,0.000033794,0.00003700039,0.0001250439,0.0001304886,0.00002578308,0.00002757763],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3073812,"threshold_uncertainty_score":0.5432671,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01531243350935996,"score_gpt":0.2588920119911104,"score_spread":0.2435795784817505,"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."}}