{"id":"W4391044918","doi":"10.1101/2024.01.18.576245","title":"Self-Supervised Transformer Model Training for a Sleep-EEG Foundation Model","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; National Center for Research Resources; National Institutes of Health; Case Western Reserve University; University of Washington; York University; Johns Hopkins University; National Heart, Lung, and Blood Institute; University of California, Davis; University of Minnesota","keywords":"Transformer; Electroencephalography; Computer science; Sleep (system call); Foundation (evidence); Artificial intelligence; Psychology; Engineering; Electrical engineering; Voltage; Neuroscience; Political science","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001277469,0.000797946,0.0006511543,0.0004296629,0.0002678917,0.00061774,0.001113449,0.001053858,0.003126572],"category_scores_gemma":[0.003915464,0.0004088195,0.0008618741,0.0003289118,0.000460176,0.0007996015,0.0006939222,0.001920373,0.0009412747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006354304,"about_ca_system_score_gemma":0.001141521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007198639,"about_ca_topic_score_gemma":0.01006255,"domain_scores_codex":[0.9997396,0.0000865776,0.00001535179,0.00008868407,0.00003211128,0.00003774328],"domain_scores_gemma":[0.9987177,0.0008435568,0.00005841211,0.00009691161,0.0002417573,0.00004157045],"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":[0.00030518,0.0001486089,0.002688666,0.0001101274,0.00008224609,0.000104661,0.0001033591,0.8498111,0.004120121,0.006290314,0.00534931,0.1308863],"study_design_scores_gemma":[0.000005422776,0.00001145965,0.0001031454,0.000003153126,0.000003677849,0.000007473418,0.000003451571,0.9984279,0.0002983826,0.0009980508,0.0001357012,0.000002179255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08647267,0.0004470188,0.9068291,0.0005887967,0.00009614135,0.0001094894,0.0004454298,0.002239911,0.002771495],"genre_scores_gemma":[0.8812615,0.0001592877,0.1108589,0.0003921316,0.00006144948,0.0002372816,0.001449905,0.0002045062,0.005375142],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007198639,"threshold_uncertainty_score":0.01431346,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04821990375105378,"score_gpt":0.2647744253116793,"score_spread":0.2165545215606255,"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."}}