{"id":"W4382318486","doi":"10.1609/aaai.v37i13.26941","title":"Robust Training for AC-OPF (Student Abstract)","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Power System Reliability and Maintenance","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Univariate; Artificial neural network; Power flow; Training (meteorology); Training set; Machine learning; Multivariate statistics; Test data; Electric power system; Artificial intelligence; Mathematical optimization; Power (physics); Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001484023,0.000689043,0.0005937435,0.0004617876,0.0003207664,0.0005715719,0.0009076608,0.0007938267,0.004562149],"category_scores_gemma":[0.007565636,0.0004191188,0.0004407615,0.0004521553,0.0004178215,0.0008441187,0.0007067059,0.001379431,0.0008670445],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006652387,"about_ca_system_score_gemma":0.000691705,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007907988,"about_ca_topic_score_gemma":0.005781183,"domain_scores_codex":[0.9994649,0.0001596228,0.0000258889,0.0001445452,0.0001561845,0.00004883337],"domain_scores_gemma":[0.9975695,0.001505773,0.0001678385,0.0002593098,0.00044826,0.00004934861],"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":[0.00009314463,0.00004863626,0.0007230976,0.00004856952,0.00003043704,0.00003946761,0.00002653437,0.8571694,0.002654489,0.002970399,0.001751444,0.1344443],"study_design_scores_gemma":[0.000002093856,0.00001095031,0.00008982261,0.000002462295,0.000001463328,0.000004669693,0.000001450916,0.9981353,0.0008144911,0.0007307925,0.0002047021,0.000001732886],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02366988,0.000343253,0.9706674,0.0002552647,0.00005712487,0.00004154429,0.00007774451,0.001521295,0.003366431],"genre_scores_gemma":[0.749432,0.0001901918,0.2454516,0.0001261717,0.00007723126,0.0001488037,0.0003160577,0.0003003365,0.003957768],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007907988,"threshold_uncertainty_score":0.01572394,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1694692866971276,"score_gpt":0.3051743531279094,"score_spread":0.1357050664307818,"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."}}