{"id":"W4412413527","doi":"10.1007/s44267-025-00085-y","title":"DASFormer: self-supervised pretraining for earthquake monitoring","year":2025,"lang":"en","type":"article","venue":"Visual Intelligence","topic":"Seismology and Earthquake Studies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; California Institute of Technology","keywords":"Computer science; Anomaly detection; Scalability; Task (project management); Anomaly (physics); Earthquake prediction; Supervised learning; Data mining; SIGNAL (programming language); Artificial intelligence; Machine learning; Seismology; Geology; Artificial neural network; Engineering; Systems 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":[0.0003858261,0.0001772434,0.0002095509,0.0001588403,0.0003940305,0.0001070629,0.0006854438,0.0001023478,0.000008606662],"category_scores_gemma":[0.0001806089,0.0001700586,0.0001017713,0.0005504829,0.00007270893,0.0003314723,0.0002239436,0.0001621077,0.00005739606],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002653468,"about_ca_system_score_gemma":0.00009034808,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000013936,"about_ca_topic_score_gemma":0.000002947114,"domain_scores_codex":[0.9986281,0.00004136012,0.0002940106,0.0004563809,0.0001374464,0.0004426865],"domain_scores_gemma":[0.9989719,0.0004533625,0.0000517705,0.0003199597,0.0001439499,0.00005908253],"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":[0.00001860365,0.00008201483,0.00589188,0.00006028795,0.0001045935,0.00000471151,0.00311828,0.0001074121,0.0001768105,0.06349786,0.0002713257,0.9266662],"study_design_scores_gemma":[0.0006416834,0.001221398,0.02742761,0.0004192647,0.00007872566,0.00002273182,0.003169484,0.7773843,0.1102264,0.04472392,0.03351919,0.001165232],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08031654,0.0006701638,0.9135717,0.0005590849,0.001591331,0.0002880017,0.000001308252,0.0003715762,0.002630367],"genre_scores_gemma":[0.9098273,0.0001074172,0.08893283,0.0003501856,0.0001157023,0.00007778964,9.752096e-7,0.000006939315,0.0005808608],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.925501,"threshold_uncertainty_score":0.6934789,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03331204904105856,"score_gpt":0.3377032223507908,"score_spread":0.3043911733097322,"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."}}