{"id":"W6921199962","doi":"10.6084/m9.figshare.29087281","title":"Additional file 2 of Dynamic clustering of genomics cohorts beyond race, ethnicity—and ancestry","year":2025,"lang":"en","type":"article","venue":"Figshare","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Cluster analysis; Genomics; Population; Genome; Genetic data","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002516708,0.001404142,0.001541059,0.003029275,0.001383998,0.003151147,0.002232634,0.001425607,0.7879152],"category_scores_gemma":[0.03843104,0.0008570889,0.001520725,0.004422416,0.0004098872,0.001690086,0.001813544,0.001241227,0.1693288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009489892,"about_ca_system_score_gemma":0.002151949,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01121629,"about_ca_topic_score_gemma":0.02032376,"domain_scores_codex":[0.9986903,0.0002767736,0.0001596293,0.0005044539,0.0001942668,0.0001745533],"domain_scores_gemma":[0.971142,0.02299395,0.001001736,0.002221983,0.001744921,0.0008954725],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002267635,0.00004384325,0.005413646,0.00127037,0.0001381485,0.00008769576,0.000109079,0.000636331,0.0001642888,0.001079775,0.9840343,0.00679574],"study_design_scores_gemma":[0.003161447,0.0001834593,0.04202426,0.001876658,0.0005049607,0.0008605196,0.0005259516,0.004018882,0.001093391,0.02570285,0.9198138,0.0002337363],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0002419047,0.00002311038,0.0007548137,0.00008664704,0.00003855345,0.00003588566,0.9974214,0.000780821,0.0006168893],"genre_scores_gemma":[0.01023336,0.0001283314,0.008123101,0.0006109178,0.0001518672,0.0009759131,0.9700502,0.00290006,0.006826209],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.7879152,"threshold_uncertainty_score":0.3025132,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01445173449385482,"score_gpt":0.2681865599028932,"score_spread":0.2537348254090384,"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."}}