{"id":"W4408312801","doi":"10.2196/71358","title":"Assessment of Recommendations Provided to Athletes Regarding Sleep Education by GPT-4o and Google Gemini: Comparative Evaluation Study","year":2025,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Sleep and related disorders","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Preprint; Athletes; Psychology; Medicine; Computer science; Physical therapy; World Wide Web","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.02801826,0.0009117984,0.00142384,0.002271348,0.0005398755,0.001389841,0.001028373,0.001022964,0.001838356],"category_scores_gemma":[0.0903862,0.0004501462,0.0015386,0.001280622,0.0007962351,0.00199005,0.00168892,0.0009413555,0.0005985889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001534487,"about_ca_system_score_gemma":0.001787162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003482885,"about_ca_topic_score_gemma":0.006230122,"domain_scores_codex":[0.9772953,0.01555881,0.002736362,0.001162688,0.002703046,0.0005437117],"domain_scores_gemma":[0.8964763,0.07453196,0.007875385,0.003877979,0.01430608,0.00293233],"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":[0.0222016,0.01043951,0.3617311,0.01368463,0.001588568,0.0009974601,0.049435,0.005355524,0.009561975,0.0005671845,0.01058807,0.5138495],"study_design_scores_gemma":[0.003243581,0.04067591,0.8574811,0.002998721,0.002584685,0.0008259958,0.02514648,0.03702426,0.009430671,0.0006065108,0.01937426,0.0006078394],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9913948,0.0003591814,0.002594783,0.0001662319,0.0000544892,0.002035348,0.0008796733,0.0003784106,0.002137027],"genre_scores_gemma":[0.967229,0.0006443529,0.02327608,0.0001832431,0.00006263842,0.004967568,0.002025015,0.0001000087,0.001512126],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02801826,"threshold_uncertainty_score":0.1481766,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08782063764236837,"score_gpt":0.5350529029754355,"score_spread":0.4472322653330671,"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."}}