{"id":"W4323049554","doi":"10.1017/s0022377823000041","title":"Beyond analytic approximations with machine learning inference of plasma parameters and confidence intervals","year":2023,"lang":"en","type":"article","venue":"Journal of Plasma Physics","topic":"Laser-induced spectroscopy and plasma","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Plasma; Inference; Physics; Langmuir probe; Statistical physics; Electron; Plasma parameter; Process (computing); Kinetic energy; Plasma parameters; Computational physics; Construct (python library); Algorithm; Machine learning; Applied mathematics; Artificial intelligence; Plasma diagnostics; Computer science; Classical mechanics; Quantum mechanics; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0002335316,0.0001636683,0.0003625066,0.0001529983,0.00005686637,0.00004866998,0.0001521686,0.00005545882,0.00001119655],"category_scores_gemma":[0.0001054982,0.0001340382,0.00007010152,0.0004630241,0.00007313238,0.0003583585,0.00002734314,0.0004883124,0.0000120683],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003159214,"about_ca_system_score_gemma":0.0000465354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001021105,"about_ca_topic_score_gemma":0.00002568195,"domain_scores_codex":[0.999007,0.00003864224,0.0003914617,0.0001005636,0.0002625265,0.0001997843],"domain_scores_gemma":[0.9989335,0.0004931008,0.0002580582,0.0001136016,0.0001039901,0.00009775438],"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":[0.0001210304,0.00006206227,0.006001274,0.000360289,0.0004906789,0.00006539012,0.002219449,0.929458,0.05327103,0.003317607,0.0002118158,0.004421358],"study_design_scores_gemma":[0.0008449803,0.000529087,0.00115979,0.0003541533,0.0001462784,0.00009464318,0.0003583257,0.8167205,0.1764067,0.003054393,0.00009059464,0.0002404679],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9917288,0.00002104582,0.007373014,0.00004778533,0.0001316379,0.00006616135,0.00001915724,0.00005016754,0.0005622465],"genre_scores_gemma":[0.9964952,0.0001497412,0.003220565,0.000006931153,0.00004428419,0.000002044857,0.00000691999,0.00002218363,0.00005211383],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1231357,"threshold_uncertainty_score":0.5465918,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01820376889366829,"score_gpt":0.2436814672218361,"score_spread":0.2254776983281678,"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."}}