{"id":"W4410571938","doi":"10.2196/75215","title":"Validation of The Umbrella Collaboration for Tertiary Evidence Synthesis in Geriatrics: Mixed Methods Study","year":2025,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Concordance; Computer science; Metric (unit); Categorical variable; Identification (biology); Higher education; Scale (ratio); Comparative effectiveness research; Benchmarking; Health care; Statistics; Psychology; Medicine; Machine learning; Mathematics; Operations management; Engineering; Management","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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5253181,0.00168479,0.004468073,0.01082982,0.002675611,0.006745268,0.00379535,0.002396705,0.005251348],"category_scores_gemma":[0.7158445,0.001785085,0.008029055,0.01112157,0.002360957,0.004144209,0.008333993,0.00171882,0.0008904155],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007746867,"about_ca_system_score_gemma":0.02542171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001888466,"about_ca_topic_score_gemma":0.004178879,"domain_scores_codex":[0.3234265,0.5326144,0.08963779,0.0134042,0.03916577,0.001751306],"domain_scores_gemma":[0.1723189,0.5965216,0.08653507,0.05563481,0.08584049,0.00314909],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.02243136,0.001597867,0.07689919,0.1989066,0.03814192,0.0005259991,0.03021529,0.004989156,0.006303766,0.01121939,0.009337649,0.5994318],"study_design_scores_gemma":[0.03505488,0.05053545,0.2247644,0.2430729,0.1077505,0.002041142,0.02154427,0.05619169,0.03802177,0.03090357,0.1884714,0.001647996],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"protocol","genre_gemma":"empirical","genre_scores_codex":[0.2414056,0.04141174,0.3342434,0.00350015,0.001810867,0.3558377,0.006538516,0.001567044,0.01368491],"genre_scores_gemma":[0.3157158,0.002552092,0.3844434,0.001134116,0.000265787,0.2937836,0.001326053,0.0002422614,0.0005367553],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4746819,"threshold_uncertainty_score":0.5853673,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5904427860719018,"score_gpt":0.7583092777898878,"score_spread":0.167866491717986,"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."}}