{"id":"W6958654664","doi":"10.6084/m9.figshare.29087302","title":"Additional file 9 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":[0.00246272,0.001565386,0.001676443,0.003128927,0.001394492,0.003324004,0.002313743,0.001488548,0.796052],"category_scores_gemma":[0.03714379,0.0009047377,0.001694272,0.004372735,0.0003926011,0.001815858,0.001979443,0.001270695,0.1899173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009621712,"about_ca_system_score_gemma":0.002033223,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01136947,"about_ca_topic_score_gemma":0.02022782,"domain_scores_codex":[0.9986113,0.0002899913,0.0001784286,0.0005103455,0.000213188,0.0001966627],"domain_scores_gemma":[0.9736435,0.02065917,0.0009634796,0.002212931,0.001649751,0.0008711064],"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":[0.0002350062,0.00004215012,0.004962213,0.001158166,0.0001512737,0.00009168161,0.00009945891,0.0005475549,0.0001670198,0.0009323038,0.9849313,0.006681841],"study_design_scores_gemma":[0.003190428,0.0001765092,0.04311271,0.00198265,0.000484373,0.0007644925,0.000496481,0.003743428,0.001197121,0.02524676,0.9193578,0.0002472341],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.0002421019,0.00002463458,0.0006920726,0.00009307727,0.0000467751,0.00003237206,0.9971185,0.00107749,0.0006730969],"genre_scores_gemma":[0.00972674,0.0001358517,0.00716881,0.0005852832,0.0001543955,0.0008092664,0.9709193,0.003301731,0.007198547],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.796052,"threshold_uncertainty_score":0.2909071,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01473710592687718,"score_gpt":0.2685339728925782,"score_spread":0.253796866965701,"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."}}