{"id":"W4417116972","doi":"10.64898/2025.12.01.691644","title":"Scaling the PBWT for Long-Range Shared Ancestry Detection in Large Haplotype Panels","year":2025,"lang":"","type":"article","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Scalability; Tree traversal; Population; Speedup; Tree (set theory); Computation; Chromosome; Search engine indexing","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":[0.002258348,0.001068471,0.001125009,0.001879762,0.001018723,0.002203918,0.002484434,0.001097176,0.01035423],"category_scores_gemma":[0.01606072,0.001037788,0.001278003,0.003545479,0.0008949426,0.004173491,0.0030163,0.001863284,0.007816321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000866227,"about_ca_system_score_gemma":0.002292669,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007114312,"about_ca_topic_score_gemma":0.009390327,"domain_scores_codex":[0.9974985,0.000601783,0.0002317265,0.000573459,0.0008998108,0.0001947108],"domain_scores_gemma":[0.9949052,0.002394738,0.0003295306,0.001438305,0.000683043,0.0002492685],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002146817,0.0003786635,0.01925111,0.0008424628,0.0003570551,0.0006263184,0.00104551,0.05869731,0.047015,0.02532228,0.100327,0.7439905],"study_design_scores_gemma":[0.0003774565,0.0002140797,0.004227952,0.00008815345,0.0000994243,0.0005190545,0.0004724335,0.8756093,0.02870501,0.06051645,0.02906352,0.0001071945],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1192316,0.001685064,0.7944348,0.001457236,0.0004307286,0.0002845669,0.007451953,0.06845243,0.006571586],"genre_scores_gemma":[0.2075349,0.0002771672,0.77707,0.0004347092,0.0000927786,0.0003710567,0.008088594,0.003304858,0.002825942],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01035423,"threshold_uncertainty_score":0.03463835,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01736251863959544,"score_gpt":0.2573757388897147,"score_spread":0.2400132202501192,"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."}}