{"id":"W4407085131","doi":"10.1016/j.compbiomed.2025.109735","title":"S4Sleep: Elucidating the design space of deep-learning-based sleep stage classification models","year":2025,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Sleep (system call); Stage (stratigraphy); Space (punctuation); Machine learning; Deep learning; Biology; Operating system","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006148591,0.0001097913,0.0002130065,0.0001542075,0.0001096067,0.000006962737,0.0002745742,0.00007924806,0.000006047749],"category_scores_gemma":[0.0003278102,0.00006850382,0.00001847709,0.0002669091,0.0005369268,0.00004075781,0.00007699805,0.0002377103,5.739927e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000157018,"about_ca_system_score_gemma":0.00001848415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001536978,"about_ca_topic_score_gemma":0.000003726255,"domain_scores_codex":[0.9987326,0.0004839246,0.0002542926,0.000302915,0.00006067686,0.0001655622],"domain_scores_gemma":[0.9975696,0.002074664,0.0001259225,0.0001758928,0.00002758343,0.00002634132],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003766021,0.0001897779,0.01131067,0.000228503,0.00004455167,0.00001615148,0.004668154,0.1560925,0.4361336,0.2017334,0.0008871937,0.1883189],"study_design_scores_gemma":[0.0007637462,0.0002795561,0.001623165,0.0001493401,0.000008959925,0.000002443084,0.0001970626,0.9605976,0.03063123,0.00503157,0.0006445962,0.00007067309],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09714212,0.0004260547,0.8964771,0.004460684,0.0004254217,0.0002094276,7.188797e-7,0.00003417061,0.0008243285],"genre_scores_gemma":[0.9948314,0.00006605588,0.003374893,0.001610795,0.00003863626,0.000008707571,0.000002694961,0.000003928566,0.00006289446],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8976893,"threshold_uncertainty_score":0.2793505,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05220474626119127,"score_gpt":0.3294087005516907,"score_spread":0.2772039542904995,"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."}}