{"id":"W4393306343","doi":"10.1101/2024.03.26.586646","title":"ntRoot: Computational Inference of Human Ancestry at Scale from Genomic Data","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Forensic and Genetic Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"Canadian Institutes of Health Research; National Institutes of Health","keywords":"Inference; Scale (ratio); Data science; Computational biology; Computer science; Evolutionary biology; Biology; Artificial intelligence; Geography; Cartography","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003073776,0.0003343848,0.0003685006,0.00008924453,0.00009423978,0.00008350312,0.001137175,0.0004579349,0.00006987806],"category_scores_gemma":[0.00007761837,0.0003533782,0.0001004512,0.0001287607,0.0003392841,0.000004220223,0.004981983,0.0004285327,0.00006912765],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006468238,"about_ca_system_score_gemma":0.0007476817,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001647289,"about_ca_topic_score_gemma":0.00003233413,"domain_scores_codex":[0.9975898,0.00008239359,0.000445591,0.001190586,0.0003554846,0.0003361999],"domain_scores_gemma":[0.9973429,0.00002936964,0.0002129395,0.001976519,0.000276424,0.000161787],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003018656,0.00005146356,0.01006661,0.0002222462,0.0001967541,0.00001004139,0.00000422736,0.000446718,0.9858767,0.00008525072,0.003004766,0.000005028475],"study_design_scores_gemma":[0.0005539417,0.0001441262,0.1679267,0.0003433596,0.0001360816,2.741651e-8,0.000003310377,0.002493353,0.8223346,0.0001112426,0.005201754,0.0007514652],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9907184,0.004635053,0.0006782227,0.00009364419,0.0004405541,0.0002864486,0.003085915,0.00003479282,0.00002702202],"genre_scores_gemma":[0.9939307,0.0002517437,0.004956016,0.00005337413,0.0006019765,0.00003088756,0.0000741226,0.00007031907,0.00003083827],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1635421,"threshold_uncertainty_score":0.9998918,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03681819833290514,"score_gpt":0.2997241585844774,"score_spread":0.2629059602515722,"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."}}