{"id":"W4401970743","doi":"10.1101/2024.08.26.609770","title":"Characterizing features affecting local ancestry inference performance in admixed populations","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Institute of Mental Health; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Inference; Evolutionary biology; R package; Computer science; Geography; Genealogy; Artificial intelligence; Biology; Statistics; Mathematics; History","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":[],"consensus_categories":[],"category_scores_codex":[0.02983204,0.0006871776,0.0006868984,0.0009255771,0.001241551,0.001934408,0.001440958,0.0009840135,0.001402876],"category_scores_gemma":[0.1046978,0.0005605165,0.0009575963,0.001020369,0.001606511,0.002030478,0.00143323,0.001377844,0.0003204024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008712017,"about_ca_system_score_gemma":0.001395167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01283129,"about_ca_topic_score_gemma":0.01786466,"domain_scores_codex":[0.9924818,0.004801973,0.0004135486,0.001517468,0.0005311355,0.0002541577],"domain_scores_gemma":[0.9468127,0.04240463,0.002149166,0.005702155,0.002457193,0.0004742653],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008209803,0.0001276765,0.5724989,0.0002772702,0.001166096,0.0004669606,0.003398226,0.3306599,0.008611463,0.009583712,0.001814348,0.07057444],"study_design_scores_gemma":[0.0001506604,0.0003959992,0.07912014,0.0001839219,0.0004418339,0.0005247602,0.001159898,0.869554,0.01210049,0.03357073,0.002674105,0.0001235731],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8208959,0.000628321,0.1741302,0.0005518541,0.00004173568,0.0001058865,0.0006265659,0.001066945,0.001952655],"genre_scores_gemma":[0.9533775,0.0001074476,0.0452208,0.0001341887,0.000009966902,0.00006482511,0.0006931319,0.0001630728,0.0002289938],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02983204,"threshold_uncertainty_score":0.1577688,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02436686740903024,"score_gpt":0.2728181883394821,"score_spread":0.2484513209304518,"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."}}