{"id":"W2083355945","doi":"10.1038/nmeth.2855","title":"Sleep-spindle detection: crowdsourcing and evaluating performance of experts, non-experts and automated methods","year":2014,"lang":"en","type":"article","venue":"Nature Methods","topic":"Sleep and Wakefulness Research","field":"Neuroscience","cited_by":380,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"National Center for Research Resources; National Center for Advancing Translational Sciences; National Institute of Neurological Disorders and Stroke; National Heart, Lung, and Blood Institute; Canadian Institutes of Health Research","keywords":"Crowdsourcing; Computer science; Polysomnography; Identification (biology); Sleep (system call); Population; Artificial intelligence; Electroencephalography; Gold standard (test); Machine learning; Data mining; Data science; Medicine; Psychology; Neuroscience; World Wide Web; Biology","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009793873,0.001753573,0.001541987,0.002878991,0.00119484,0.001212173,0.002077032,0.002678339,0.001858157],"category_scores_gemma":[0.02009833,0.0003545175,0.001131872,0.001361213,0.0008566966,0.001205863,0.002726808,0.0009578774,0.001688585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007807029,"about_ca_system_score_gemma":0.001349423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009494409,"about_ca_topic_score_gemma":0.01128486,"domain_scores_codex":[0.9923325,0.003108311,0.0004021727,0.001751457,0.001954371,0.0004512206],"domain_scores_gemma":[0.9839045,0.009115583,0.00108501,0.002104277,0.002925069,0.0008653851],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0128292,0.004916302,0.0971612,0.003976815,0.00317459,0.001098086,0.003245869,0.1383691,0.04727289,0.002780329,0.02933442,0.6558412],"study_design_scores_gemma":[0.001395389,0.003051416,0.1192961,0.0003097036,0.000615529,0.0008765803,0.00234228,0.8254552,0.0225158,0.008823014,0.01500288,0.0003160095],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.843663,0.002396134,0.1314211,0.0007158227,0.001226946,0.001596278,0.00310126,0.004522433,0.01135695],"genre_scores_gemma":[0.9273314,0.0003093006,0.06283868,0.0002944462,0.0002755474,0.0004724883,0.003633478,0.0002460524,0.004598589],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9902061,"threshold_uncertainty_score":0.0517956,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0476372112603679,"score_gpt":0.4604568082439071,"score_spread":0.4128195969835392,"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."}}