{"id":"W4413385345","doi":"10.1088/1741-4326/adfdfb","title":"Neural operator surrogate models of plasma edge simulations: feasibility and data efficiency","year":2025,"lang":"en","type":"article","venue":"Nuclear Fusion","topic":"Magnetic confinement fusion research","field":"Physics and Astronomy","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Enhanced Data Rates for GSM Evolution; Operator (biology); Plasma; Surrogate model; Artificial neural network; Statistical physics; Computer science; Physics; Artificial intelligence; Nuclear physics; Machine learning","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001933503,0.00008086077,0.000123841,0.00006659293,0.0001326692,0.00004017313,0.0002914027,0.00002524869,0.01529048],"category_scores_gemma":[0.00002672377,0.00007259663,0.00002128046,0.0001851992,0.00006732667,0.00005539774,0.0007856535,0.00009774548,0.000007608742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004042479,"about_ca_system_score_gemma":0.00005184242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004033907,"about_ca_topic_score_gemma":0.00002732727,"domain_scores_codex":[0.9991553,0.00005561713,0.0002006797,0.0002910303,0.0001638281,0.0001335215],"domain_scores_gemma":[0.9991727,0.00008840403,0.0000378524,0.0005684351,0.00008563047,0.00004693396],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002347639,0.0009443944,0.03277583,0.0001719997,0.00004010948,0.000001362252,0.0005252748,0.002401267,0.05818392,0.02381513,0.00876612,0.8721398],"study_design_scores_gemma":[0.000788233,0.00004139242,0.007223921,0.00002920578,0.00001261464,6.217169e-8,0.0002107214,0.9835871,0.0003390475,0.0003261925,0.007368016,0.00007349905],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9774532,0.00004479645,0.0001613739,0.0004595755,0.00005826632,0.0003498686,0.0001090687,0.00001491532,0.02134888],"genre_scores_gemma":[0.9989113,0.000007657627,0.0002318197,0.00002326724,0.00001754521,0.00000149538,0.00004455434,0.000005523716,0.0007568384],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9811859,"threshold_uncertainty_score":0.9856097,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04829904352849228,"score_gpt":0.3207297303551012,"score_spread":0.2724306868266089,"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."}}