{"id":"W4417458211","doi":"10.1038/s41746-025-02237-2","title":"SLEEPYLAND: trust begins with fair evaluation of automatic sleep staging models","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Research Resources; National Institute of Biomedical Imaging and Bioengineering; National Institute of Arthritis and Musculoskeletal and Skin Diseases; National Institute of Nursing Research; National Heart, Lung, and Blood Institute; National Institute on Aging; University of California, Davis; National Center for Advancing Translational Sciences; Johns Hopkins Bloomberg School of Public Health; Danmarks Tekniske Universitet; York University; Jazz Pharmaceuticals; National Institutes of Health; H. Lundbeck A/S; University of Minnesota; Lundbeckfonden; Case Western Reserve University; Johns Hopkins University; University of Washington; Eunice Kennedy Shriver National Institute of Child Health and Human Development; American Sleep Medicine Foundation","keywords":"Ambiguity; Ensemble forecasting; Ensemble learning; Deep learning; Multiple Models; Sleep (system call)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003133298,0.0001530292,0.0002684445,0.0002064051,0.00005379754,0.00004740488,0.0002562524,0.00003461201,0.00004437445],"category_scores_gemma":[0.0003922444,0.0001008573,0.00002961838,0.0004097775,0.0002175258,0.0004889008,0.00006187306,0.0001079018,0.000005698451],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005279801,"about_ca_system_score_gemma":0.00007311002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001219462,"about_ca_topic_score_gemma":0.00000315638,"domain_scores_codex":[0.9983782,0.00005488411,0.0003070135,0.0003149839,0.0007449082,0.0002000164],"domain_scores_gemma":[0.9991304,0.0002862753,0.0001198195,0.000277837,0.0001274398,0.0000582095],"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":[0.0002084686,0.0006414939,0.006092407,0.0008027505,0.0001674,0.0000454594,0.008607695,0.03419098,0.05552452,0.02517921,0.003795395,0.8647442],"study_design_scores_gemma":[0.002450565,0.0005360027,0.001358204,0.001025094,0.0001055688,0.00001577857,0.0005781612,0.9446525,0.03785081,0.01089496,0.0003528727,0.0001794635],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9035193,0.00008502734,0.01452981,0.001340824,0.0002736356,0.0003390625,0.00001297346,0.0001146249,0.07978473],"genre_scores_gemma":[0.9988982,0.000002974088,0.0001039801,0.0004531181,0.00005031206,0.00001570573,0.000006048402,0.0000107446,0.0004589031],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9104615,"threshold_uncertainty_score":0.4112839,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03979580373329172,"score_gpt":0.3027297654122166,"score_spread":0.2629339616789249,"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."}}