{"id":"W2049491422","doi":"10.1016/j.jenvrad.2009.08.015","title":"Machine learning for radioxenon event classification for the Comprehensive Nuclear-Test-Ban Treaty","year":2009,"lang":"en","type":"article","venue":"Journal of Environmental Radioactivity","topic":"Radioactive contamination and transfer","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Discriminator; Machine learning; Support vector machine; Artificial intelligence; Computer science; Naive Bayes classifier; Event (particle physics); Nuclear explosion; Sampling (signal processing); Treaty; Data mining; Nuclear physics; Physics; Detector","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":[],"consensus_categories":[],"category_scores_codex":[0.0004193393,0.0002045422,0.0002774867,0.00004663226,0.0004070422,0.0000365725,0.0002508699,0.00007463462,0.0003578317],"category_scores_gemma":[0.00007497585,0.0001495654,0.0003430954,0.00007467988,0.0001769356,0.0004341602,0.00001547886,0.0002934467,0.00001516559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006557249,"about_ca_system_score_gemma":0.000009012836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008256004,"about_ca_topic_score_gemma":0.000005021971,"domain_scores_codex":[0.9986897,0.000101505,0.0003659944,0.0002372952,0.0003567848,0.0002487558],"domain_scores_gemma":[0.9985623,0.0007686457,0.0003590446,0.0001723387,0.0000100298,0.000127671],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.001077427,0.001660716,0.02289416,0.00001096094,0.0001842102,0.00000751037,0.0008755205,0.004546362,0.5097545,0.0002725092,0.001294654,0.4574215],"study_design_scores_gemma":[0.002641612,0.001679619,0.8651217,0.00001100636,0.0001805486,0.0001110777,0.0003087261,0.03393245,0.005070401,0.0002072218,0.09050423,0.0002314626],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9329193,0.0005724482,0.05852942,0.005209829,0.0003072506,0.00142275,0.00008024198,0.0000264947,0.0009322481],"genre_scores_gemma":[0.9978922,0.0003537628,0.0009099213,0.0002946788,0.0001276195,0.000014104,0.00000882823,0.00002337959,0.0003755259],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8422275,"threshold_uncertainty_score":0.6099099,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01625068867046633,"score_gpt":0.2465941468187862,"score_spread":0.2303434581483199,"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."}}