{"id":"W4281885821","doi":"10.1093/sleep/zsac079.603","title":"0606 A Paradigm for Testing the Accuracy of Digital Sleep Staging Systems","year":2022,"lang":"en","type":"article","venue":"SLEEP","topic":"Health Education and Validation","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"Center for Innovations in Quality, Effectiveness and Safety; National Institutes of Health; Office of Research and Development","keywords":"Computer science; Consistency (knowledge bases); Sleep (system call); Artificial intelligence; Programming language","routes":{"ca_aff":true,"ca_fund":false,"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":[0.001021539,0.0000386319,0.00006749867,0.00003235044,0.0009726396,0.00009631523,0.0001819241,0.00001365022,0.00005375206],"category_scores_gemma":[0.001483371,0.00003299609,0.00002906345,0.0002888307,0.00004288249,0.0001651544,0.00002789868,0.00006756064,0.000004944978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001060147,"about_ca_system_score_gemma":0.0002228426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009673892,"about_ca_topic_score_gemma":0.00001639678,"domain_scores_codex":[0.9991481,0.0001366469,0.0001909727,0.00009559043,0.0002446554,0.00018402],"domain_scores_gemma":[0.9987088,0.0009011506,0.0001695234,0.0001063742,0.00006393992,0.00005023452],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004658832,0.0003815982,0.1073182,0.0003112512,0.00005277658,0.000001006999,0.2138925,0.006969109,0.0001940898,0.4241571,0.009343603,0.2373322],"study_design_scores_gemma":[0.0003532759,0.00008780726,0.003766613,0.00001898839,0.00001965103,0.000001415041,0.1090009,0.01284919,0.00002019218,0.003013443,0.8707101,0.0001583674],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.927738,0.0004197476,0.005760857,0.02826431,0.004440085,0.002955683,0.0001672295,0.0001745646,0.03007956],"genre_scores_gemma":[0.9990638,0.000001642957,0.00005834068,0.0001390238,0.000230129,0.0001849189,0.00001499181,0.000005617112,0.0003014913],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8613665,"threshold_uncertainty_score":0.7480856,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1576774117074917,"score_gpt":0.4019923387980756,"score_spread":0.2443149270905839,"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."}}