{"id":"W4417474630","doi":"10.48550/arxiv.2512.14658","title":"gridfm-datakit-v1: A Python Library for Scalable and Realistic Power Flow and Optimal Power Flow Data Generation","year":2025,"lang":"","type":"preprint","venue":"ArXiv.org","topic":"Optimal Power Flow Distribution","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Hydro-Québec; Eidgenössische Technische Hochschule Zürich; Technische Universiteit Delft","keywords":"Python (programming language); Scalability; Generator (circuit theory); Limiting; Generalization; Power flow; Scaling","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.000913902,0.001368638,0.001288059,0.0003798032,0.0005420291,0.001011851,0.001292284,0.001239734,0.0005219473],"category_scores_gemma":[0.0007311829,0.001599019,0.0002076635,0.0004916203,0.0002722464,0.002744437,0.004180457,0.001337082,0.00007873646],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002470999,"about_ca_system_score_gemma":0.000427958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000784492,"about_ca_topic_score_gemma":0.00002486128,"domain_scores_codex":[0.9937269,0.0001817349,0.00147579,0.00290001,0.0004622921,0.00125324],"domain_scores_gemma":[0.9952232,0.0003439483,0.0003334059,0.003309456,0.0002482246,0.0005418167],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002350823,0.001307713,0.04332167,0.01068375,0.003968856,0.0002861808,0.00228445,0.3732297,0.01311246,0.00299982,0.5233279,0.0231267],"study_design_scores_gemma":[0.001807748,0.0003044188,0.01355097,0.000847114,0.0007179764,0.00004565373,0.0000885327,0.9244896,0.00139658,0.0001224811,0.05500475,0.001624187],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5603248,0.01016759,0.3317798,0.002245265,0.008346182,0.004707132,0.07932531,0.001105042,0.001998823],"genre_scores_gemma":[0.7908682,0.004372644,0.1105774,0.0003853223,0.001588155,0.0004105797,0.08963655,0.0004248147,0.001736279],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5512599,"threshold_uncertainty_score":0.9999064,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04621489908001053,"score_gpt":0.2673279785027455,"score_spread":0.221113079422735,"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."}}