{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002953961,0.001007378,0.001445062,0.0008922955,0.0008286847,0.0005250913,0.0003291911,0.0006693599,0.00001277318],"category_scores_gemma":[0.001297075,0.00111308,0.001116688,0.0009493916,0.00009195288,0.0006976115,0.0003179233,0.01087118,0.0000058867],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006410948,"about_ca_system_score_gemma":0.001126457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002018547,"about_ca_topic_score_gemma":0.001290596,"domain_scores_codex":[0.9930186,0.000350931,0.001306307,0.00126734,0.0005564539,0.003500327],"domain_scores_gemma":[0.9968541,0.0006907784,0.0007972227,0.0005820538,0.0007962491,0.0002796173],"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":[0.001310771,0.0002433669,0.000736131,0.0001259213,0.009037668,0.00009659469,0.001108394,0.9738242,0.00003372631,0.009672556,0.000009902197,0.003800761],"study_design_scores_gemma":[0.002958143,0.001889297,0.001167664,0.0001895297,0.005042688,0.0004986883,0.0007181375,0.9689696,0.0000258908,0.01668846,0.0008829665,0.0009689677],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.386995,0.009293606,0.5965101,0.0005596209,0.001543701,0.001763865,0.002609131,0.0002923333,0.0004326363],"genre_scores_gemma":[0.9869626,0.01041871,0.0002662448,0.000007107008,0.000904741,0.00004006439,0.0007644946,0.00009022247,0.0005457929],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5999676,"threshold_uncertainty_score":0.9991319,"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."}}