{"id":"W6977373527","doi":"10.6084/m9.figshare.29087290","title":"Additional file 5 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":[0.00256292,0.001518301,0.001637975,0.003088553,0.001442721,0.003201923,0.002240092,0.001472295,0.7912822],"category_scores_gemma":[0.03866782,0.0008738759,0.001694304,0.004414148,0.0003966758,0.001749404,0.001881732,0.001263613,0.1700816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009900503,"about_ca_system_score_gemma":0.002119065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01243442,"about_ca_topic_score_gemma":0.02189953,"domain_scores_codex":[0.9985947,0.0003080705,0.0001726213,0.0005281655,0.0002023459,0.0001940345],"domain_scores_gemma":[0.9713808,0.02265885,0.001019559,0.002238468,0.001789418,0.0009127953],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0002526778,0.00004584022,0.005864934,0.001348748,0.0001648121,0.00009696827,0.0001203236,0.0006720755,0.0001784219,0.001058574,0.9830145,0.007182147],"study_design_scores_gemma":[0.003147661,0.0001970863,0.04605147,0.002090491,0.0005633206,0.0008546895,0.0005582579,0.004174216,0.001188728,0.02601046,0.9149116,0.0002520379],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.0002704577,0.00002746325,0.0007913725,0.000095769,0.00004729115,0.00003620161,0.9971118,0.0009503668,0.0006691948],"genre_scores_gemma":[0.01112153,0.0001419685,0.008028045,0.0006413995,0.0001602974,0.0008835381,0.9688101,0.002989667,0.007223452],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7912822,"threshold_uncertainty_score":0.2977106,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01472514665617706,"score_gpt":0.2685051275933125,"score_spread":0.2537799809371354,"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."}}