{"id":"W7127404481","doi":"10.1109/ccece64018.2025.11364384","title":"Evaluating Power Quality Monitoring Devices: A Hydro-Québec Benchmark Using Statistical and Machine Learning Methods","year":2025,"lang":"","type":"article","venue":"","topic":"Power Quality and Harmonics","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hydro-Québec","funders":"","keywords":"Benchmark (surveying); Reliability (semiconductor); Linear discriminant analysis; Process (computing); Matching (statistics); Partial least squares regression; Quality (philosophy); Feature selection; Statistical process control","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008504604,0.0007229132,0.00110784,0.0003122078,0.000866499,0.0004752806,0.000337588,0.0004161905,0.001081721],"category_scores_gemma":[0.002981646,0.0007965012,0.0001769357,0.0006847903,0.0002139707,0.0004595942,0.0005423162,0.001727977,0.00001536354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007212748,"about_ca_system_score_gemma":0.000599327,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0167906,"about_ca_topic_score_gemma":0.0007453699,"domain_scores_codex":[0.9933198,0.002333341,0.001761681,0.0009640809,0.0005538314,0.001067234],"domain_scores_gemma":[0.9940808,0.00456237,0.0002503169,0.0005518185,0.0001856651,0.0003690084],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005363059,0.0005819447,0.1229571,0.009590154,0.003891497,0.00007544452,0.02305375,0.15869,0.1036018,0.06559573,0.00008413848,0.5113422],"study_design_scores_gemma":[0.001215151,0.0001524141,0.01141247,0.00088572,0.0005730135,0.00001255522,0.002338632,0.9713894,0.004873749,0.001623257,0.004467746,0.001055926],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2695727,0.02033399,0.6991823,0.0002240043,0.001375418,0.0003948467,0.00003816604,0.0003001103,0.008578483],"genre_scores_gemma":[0.6608825,0.0002854753,0.3380069,0.0000862595,0.00008732137,0.00001099982,0.000009343984,0.00005913395,0.0005720541],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8126994,"threshold_uncertainty_score":0.9998314,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1623227504019954,"score_gpt":0.4713065968409549,"score_spread":0.3089838464389596,"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."}}