{"id":"W6893100774","doi":"10.5281/zenodo.14042803","title":"Human ancestry inference at scale, from genomic data","year":2024,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"Canadian Institutes of Health Research","keywords":"Inference; Code (set theory); Scripting language; Genetic data; R package; Genetic genealogy","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.004440015,0.001123533,0.001176387,0.002438696,0.001212663,0.002982039,0.00187289,0.000935458,0.08211631],"category_scores_gemma":[0.02446877,0.001538513,0.001403386,0.003382804,0.001001736,0.002154604,0.003724038,0.002060688,0.04755004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007581789,"about_ca_system_score_gemma":0.002109334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006755271,"about_ca_topic_score_gemma":0.01161234,"domain_scores_codex":[0.9981103,0.0006366646,0.0001403971,0.0005203803,0.0004976673,0.00009451052],"domain_scores_gemma":[0.9952453,0.002480115,0.000167715,0.001427644,0.0004394243,0.0002396902],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007272421,0.00007818633,0.006648929,0.001191592,0.0003231831,0.0005182299,0.001141866,0.005690868,0.00660117,0.01787649,0.8699954,0.08920675],"study_design_scores_gemma":[0.001046911,0.00007027726,0.01912536,0.0006351368,0.0002563233,0.001210062,0.0005377387,0.0605531,0.01292342,0.09792928,0.8053765,0.0003360282],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.0099247,0.0006428071,0.3714031,0.001684085,0.0008155974,0.0003500035,0.380865,0.2124801,0.02183462],"genre_scores_gemma":[0.05249367,0.0006136462,0.4306432,0.0007418654,0.0002593346,0.0009591075,0.407464,0.09658765,0.01023747],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.08211631,"threshold_uncertainty_score":0.2747064,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07561895945303186,"score_gpt":0.3157009443801012,"score_spread":0.2400819849270693,"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."}}