{"id":"W4408669733","doi":"10.2196/65968","title":"Calibration and Validation of Machine Learning Models for Physical Behavior Characterization: Protocol and Methods for the Free-Living Physical Activity in Youth (FLPAY) Study","year":2025,"lang":"en","type":"article","venue":"JMIR Research Protocols","topic":"Physical Activity and Health","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development","keywords":"Preprint; Protocol (science); Calibration; Computer science; Test (biology); Psychology; Physical activity; Artificial intelligence; Machine learning; Medicine; Statistics; Physical medicine and rehabilitation; World Wide Web; Mathematics; Alternative medicine","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":[0.03995533,0.002246378,0.001278046,0.001235597,0.001561672,0.001257989,0.002707947,0.002089978,0.006336081],"category_scores_gemma":[0.05504041,0.001156347,0.002319923,0.001195322,0.001773049,0.0007298531,0.00301788,0.003012922,0.003451822],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001284036,"about_ca_system_score_gemma":0.004809492,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003117318,"about_ca_topic_score_gemma":0.003446853,"domain_scores_codex":[0.977476,0.01327588,0.002032146,0.003479165,0.003055142,0.0006816025],"domain_scores_gemma":[0.9610239,0.01146954,0.002991613,0.01144772,0.01216577,0.0009015094],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.03307727,0.02715804,0.1682428,0.004510265,0.002550147,0.001396896,0.005149716,0.1030332,0.0436453,0.01963932,0.06310081,0.5284962],"study_design_scores_gemma":[0.01427374,0.04290391,0.3543431,0.00312493,0.00209895,0.001721127,0.002356254,0.2170428,0.08154594,0.03237519,0.2471832,0.001030843],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"protocol","genre_scores_codex":[0.1958032,0.0008246997,0.6032114,0.000677951,0.0005767705,0.1753223,0.01405925,0.002177153,0.007347209],"genre_scores_gemma":[0.175946,0.0003822003,0.285714,0.0006101769,0.0001478766,0.5218476,0.01184647,0.0004792504,0.003026553],"genre_candidate":"protocol","genre_consensus":null,"teacher_disagreement_score":0.03995533,"threshold_uncertainty_score":0.2113065,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3880527861256483,"score_gpt":0.612388334576786,"score_spread":0.2243355484511377,"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."}}