{"id":"W2730761802","doi":"10.1093/gji/ggx238","title":"Supervised machine learning on a network scale: application to seismic event classification and detection","year":2017,"lang":"en","type":"article","venue":"Geophysical Journal International","topic":"Seismology and Earthquake Studies","field":"Computer Science","cited_by":91,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Waveform; False alarm; Event (particle physics); Constant false alarm rate; Computer science; Scale (ratio); Artificial intelligence; Data mining; False positive rate; Sampling (signal processing); Pattern recognition (psychology); Seismology; Geology; Geography","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":[0.0002589297,0.0001007342,0.0001079234,0.0000660909,0.0009714015,0.0003130347,0.0005263417,0.00004395892,0.000005286884],"category_scores_gemma":[0.00008769381,0.00008938245,0.00005396957,0.00005631263,0.00004823391,0.000344483,0.0001915508,0.0003333257,0.0001043211],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004539705,"about_ca_system_score_gemma":0.00001629529,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004173912,"about_ca_topic_score_gemma":0.0000176739,"domain_scores_codex":[0.9990993,0.00006092212,0.0001691259,0.0002507348,0.0002495626,0.0001704019],"domain_scores_gemma":[0.9993264,0.00006523154,0.0001684035,0.0002166229,0.0001251263,0.00009818296],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001544445,0.0001433884,0.02090655,0.000003731126,0.0001138068,0.00001228642,0.0004858529,0.01194621,0.003590302,0.01545118,0.0004683783,0.9467239],"study_design_scores_gemma":[0.0002814607,0.0001548861,0.5726641,0.00001842597,0.000005515315,0.00006082201,0.00001140563,0.4120958,0.0002177937,0.007209582,0.007182012,0.00009820047],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4455109,0.00002236767,0.5408199,0.01205677,0.0007932661,0.00008523432,0.000001111457,0.00003725238,0.0006731987],"genre_scores_gemma":[0.9965671,0.00003619361,0.001557843,0.0007495575,0.0008294329,0.00001638744,0.000002593515,0.000005248171,0.0002356874],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9466256,"threshold_uncertainty_score":0.7471334,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01437948479481187,"score_gpt":0.2672439522893857,"score_spread":0.2528644674945739,"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."}}