{"id":"W3135079163","doi":"10.1007/s00521-021-05872-4","title":"Deep and confident prediction for a laboratory earthquake","year":2021,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Earthquake Detection and Analysis","field":"Earth and Planetary Sciences","cited_by":22,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial neural network; Computer science; Fault (geology); Raw data; Convolutional neural network; Earthquake prediction; Deep learning; Artificial intelligence; Machine learning; Data mining; Reliability engineering; Seismology; Geology; Engineering","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":[0.00009149693,0.00005581205,0.00007686236,0.0000278132,0.0003262225,0.00007970888,0.00002308328,0.00003067052,0.00006581286],"category_scores_gemma":[0.00001658487,0.00005322226,0.00002453832,0.0001640614,0.00003884689,0.00004153807,0.000006153673,0.00006487635,0.000007823346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":6.250202e-7,"about_ca_system_score_gemma":0.00001191153,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003727742,"about_ca_topic_score_gemma":0.0003732027,"domain_scores_codex":[0.9995059,0.00002906889,0.0001100291,0.0002008976,0.00005760479,0.00009647412],"domain_scores_gemma":[0.9996288,0.0001190786,0.00003447507,0.00007649312,0.00006664155,0.00007455207],"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":[0.000007017112,0.0000167296,0.1084512,0.0000394635,0.00002670764,0.000001577867,0.0001154115,0.005035354,0.0004806679,0.0005819504,0.0001686853,0.8850752],"study_design_scores_gemma":[0.0003158878,0.00005508143,0.5130206,0.000007539413,0.00004201085,0.00003297128,0.0003610439,0.4431424,0.000357076,0.00033734,0.04220167,0.0001263642],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.959656,0.001826073,0.03691059,0.0006972137,0.00006829094,0.0001845849,0.0001074109,0.00008202738,0.0004678349],"genre_scores_gemma":[0.9985822,0.00006036857,0.0006732888,0.0002959189,0.0001285365,0.000003824795,0.00009639756,0.000001757786,0.0001576542],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8849488,"threshold_uncertainty_score":0.2509073,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01020466200559334,"score_gpt":0.2273929084157669,"score_spread":0.2171882464101735,"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."}}