{"id":"W7107872864","doi":"10.2139/ssrn.5819524","title":"Machine Learning for Physical Simulation Challenge Results and Retrospective Analysis: Power Grid Use Case","year":2025,"lang":"","type":"preprint","venue":"SSRN Electronic Journal","topic":"Optimal Power Flow Distribution","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Benchmarking; Benchmark (surveying); Key (lock); Grid; Renewable energy; Mirroring; Wind power; Work (physics)","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":[0.005752869,0.000556638,0.0007467919,0.001020391,0.0005208227,0.001417308,0.001266417,0.001222089,0.003172909],"category_scores_gemma":[0.031589,0.0003446466,0.0006802814,0.001090897,0.0006830898,0.001834076,0.0007051458,0.001248345,0.0003159097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009045941,"about_ca_system_score_gemma":0.0008637868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01027501,"about_ca_topic_score_gemma":0.007490451,"domain_scores_codex":[0.9977404,0.001251039,0.000100445,0.000320955,0.0004428672,0.0001443129],"domain_scores_gemma":[0.9739791,0.01931515,0.000996632,0.003245682,0.002184722,0.0002788085],"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":[0.000538025,0.000293875,0.02675729,0.0001036399,0.0001079055,0.0004284626,0.0001296381,0.9352561,0.0006141331,0.01201158,0.005656405,0.01810294],"study_design_scores_gemma":[0.0000142308,0.00004270699,0.002541527,0.000009193026,0.00001250813,0.00005792561,0.00005275822,0.992371,0.0005951576,0.003812692,0.0004819501,0.000008362495],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8324131,0.0002736335,0.1489045,0.00139126,0.0001028981,0.0001783229,0.004052006,0.0007851911,0.01189905],"genre_scores_gemma":[0.9832643,0.00003196648,0.01454394,0.00003893555,0.00001909315,0.00003987493,0.00123076,0.00005595304,0.0007752063],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01027501,"threshold_uncertainty_score":0.03042448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01149269014814265,"score_gpt":0.2720886452419002,"score_spread":0.2605959550937575,"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."}}