{"id":"W3084017095","doi":"10.1103/physreve.104.025205","title":"Uncovering turbulent plasma dynamics via deep learning from partial observations","year":2021,"lang":"en","type":"article","venue":"Physical review. E","topic":"Magnetic confinement fusion research","field":"Physics and Astronomy","cited_by":82,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Fusion Energy Sciences; Office of Science; U.S. Department of Energy","keywords":"Thermonuclear fusion; Turbulence; Plasma; Physics; Statistical physics; Partial differential equation; Enhanced Data Rates for GSM Evolution; Fluid dynamics; Boundary (topology); Theoretical physics; Mechanics; Computer science; Mathematics; Artificial intelligence; Nuclear physics; Quantum mechanics; Mathematical analysis","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00007825856,0.0001450832,0.0002810367,0.00001250824,0.000116983,0.00005391182,0.0001560919,0.0000134871,0.02830637],"category_scores_gemma":[0.00006209939,0.0001392533,0.0001757709,0.000248142,0.00002435816,0.00003346493,0.0001887309,0.0003001878,0.000272504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001796251,"about_ca_system_score_gemma":0.00006397784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000480645,"about_ca_topic_score_gemma":0.00007192908,"domain_scores_codex":[0.9987502,0.0001080524,0.000245165,0.0003019886,0.000334375,0.0002602369],"domain_scores_gemma":[0.9991797,0.0002119085,0.00007884205,0.0002893805,0.0001193778,0.0001207564],"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":[0.000006852239,0.0004261615,0.009614754,0.0001499189,0.0001015973,0.00001322333,0.0001033484,0.0007393265,0.00864925,0.01418028,0.001390874,0.9646244],"study_design_scores_gemma":[0.0007869189,0.00008539981,0.01225508,0.0007677103,0.0002181146,8.621006e-7,0.0001993462,0.6656287,0.006456007,0.00873406,0.3042737,0.0005941006],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9413937,0.001529837,0.01888124,0.005818196,0.0001518729,0.0004955185,0.00003207405,0.0000624651,0.03163506],"genre_scores_gemma":[0.9955166,0.0005270788,0.0005913142,0.0002476041,0.000570051,0.0001077453,0.000649112,0.00002178445,0.001768683],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9640303,"threshold_uncertainty_score":0.9725819,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02329072322889346,"score_gpt":0.3002841443305868,"score_spread":0.2769934211016933,"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."}}