{"id":"W4417473717","doi":"10.48550/arxiv.2512.14461","title":"AnySleep: a channel-agnostic deep learning system for high-resolution sleep staging in multi-center cohorts","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; York University; National Institutes of Health; Case Western Reserve University; Johns Hopkins University; National Heart, Lung, and Blood Institute; University of California, Davis; University of Minnesota; University of Washington; American Sleep Medicine Foundation","keywords":"Polysomnography; Electroencephalography; Electrooculography; Generalization; Sleep (system call); Deep learning; Sleep Stages","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":[0.001370485,0.001294419,0.0007373762,0.0007112453,0.0003595193,0.0006016063,0.001952178,0.001033383,0.003734672],"category_scores_gemma":[0.004164116,0.000523907,0.0009319768,0.0005251684,0.0002291121,0.0007235738,0.002154362,0.001763681,0.001282548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005383734,"about_ca_system_score_gemma":0.001225201,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01003619,"about_ca_topic_score_gemma":0.02221421,"domain_scores_codex":[0.9997306,0.00006836183,0.00002057162,0.0001101223,0.00003308847,0.00003712322],"domain_scores_gemma":[0.9995522,0.0001889674,0.00004264824,0.00007868397,0.00008986334,0.00004768625],"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":[0.001482645,0.0008213373,0.05908319,0.0005167113,0.001541322,0.0008921116,0.0002555267,0.170741,0.009426392,0.00280818,0.129963,0.6224687],"study_design_scores_gemma":[0.0002269997,0.0003172809,0.009177487,0.0001075858,0.00016202,0.0002323782,0.00005785161,0.9694941,0.003855323,0.00632137,0.009978319,0.00006920894],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2495585,0.004671015,0.664091,0.003084162,0.0009749274,0.0009480236,0.0416283,0.02951215,0.005532012],"genre_scores_gemma":[0.7188927,0.001539452,0.2084825,0.002383635,0.0003038598,0.001859135,0.05296656,0.001095041,0.01247716],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01003619,"threshold_uncertainty_score":0.01995558,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04924255809560761,"score_gpt":0.2866428020564999,"score_spread":0.2374002439608923,"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."}}