{"id":"W6958702703","doi":"10.6084/m9.figshare.29087308","title":"Additional file 11 of Dynamic clustering of genomics cohorts beyond race, ethnicity—and ancestry","year":2025,"lang":"en","type":"dataset","venue":"Figshare","topic":"Scientific Computing and Data Management","field":"Decision Sciences","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004528688,0.0002013453,0.0005111215,0.0004519692,0.0001015172,0.0001599062,0.001444711,0.0001684802,0.9031133],"category_scores_gemma":[0.01245179,0.0001824733,0.0001219746,0.0006359933,0.00005087961,0.0001225477,0.002382772,0.000209515,0.0002279154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003915633,"about_ca_system_score_gemma":0.0002540123,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002800293,"about_ca_topic_score_gemma":0.0003813389,"domain_scores_codex":[0.9971308,0.00008149965,0.0007891326,0.0007885341,0.001010283,0.0001997654],"domain_scores_gemma":[0.9928877,0.004457797,0.0008807887,0.001386816,0.0003148497,0.00007198955],"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":[0.000003899734,0.00002396036,5.057642e-7,0.0002773371,0.00001806371,0.000006770537,0.000007360865,0.0001298501,2.169162e-7,3.224272e-7,0.9940566,0.005475097],"study_design_scores_gemma":[0.00008123839,0.00001481804,0.0004470774,0.002368405,0.00001491678,0.000003376757,0.00004876261,0.003947269,0.000001263528,0.00007879191,0.9928443,0.000149825],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.000003355305,0.0001198587,0.000006625096,0.00001661512,0.0002944669,0.0001872323,0.9988144,0.00001131221,0.0005461263],"genre_scores_gemma":[0.000003435815,0.000008142761,0.000609341,0.00005671362,0.00004798568,0.00006390567,0.9965537,0.000004393163,0.002652376],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.9028854,"threshold_uncertainty_score":0.9958668,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08988286636610304,"score_gpt":0.3591014696115767,"score_spread":0.2692186032454736,"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."}}