{"id":"W7163682316","doi":"10.13182/t130-44811","title":"Developing a Machine Learning Benchmark Using Real-Time Data from the PUR-1 Reactor for Nuclear Applications","year":2024,"lang":"","type":"article","venue":"Transactions of the American Nuclear Society","topic":"Nuclear reactor physics and engineering","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University; CNIB Foundation; Canadian Nuclear Laboratories","funders":"","keywords":"Benchmark (surveying); Nuclear reactor; Support vector machine; Experimental data","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":[0.002530207,0.001586988,0.0007860074,0.002172963,0.0008819485,0.001350158,0.002396868,0.001871673,0.002299042],"category_scores_gemma":[0.007111971,0.0003589972,0.0007182159,0.002215322,0.0005716569,0.001265236,0.0009939512,0.001275753,0.001601323],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001145956,"about_ca_system_score_gemma":0.00157111,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01955229,"about_ca_topic_score_gemma":0.02177961,"domain_scores_codex":[0.9982418,0.0004567442,0.0001672729,0.0004579749,0.000490486,0.0001856185],"domain_scores_gemma":[0.9953067,0.001599786,0.0002321952,0.000599691,0.002028252,0.000233439],"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":[0.001334979,0.003373726,0.02578075,0.0008243524,0.0004365332,0.00109288,0.0001596456,0.56321,0.02254961,0.003056181,0.07239042,0.3057909],"study_design_scores_gemma":[0.0002139794,0.0008520691,0.01307231,0.00002934621,0.00004531929,0.0002086127,0.0001973163,0.9509181,0.0216868,0.001485168,0.01124983,0.00004119943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8719371,0.002143147,0.08148522,0.001521886,0.0009773584,0.0006990499,0.01593456,0.01252722,0.01277448],"genre_scores_gemma":[0.7899349,0.0005154555,0.1308827,0.0003824944,0.0001785394,0.0005082318,0.06827202,0.0006768353,0.008648909],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01955229,"threshold_uncertainty_score":0.03887695,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02612088275324759,"score_gpt":0.2532038301264672,"score_spread":0.2270829473732196,"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."}}