{"id":"W4410477978","doi":"10.1101/2025.05.14.653986","title":"An Updated Polygenic Index Repository: Expanded Phenotypes, New Cohorts, and Improved Causal Inference","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"National Institute on Aging; National Institutes of Health; Vetenskapsrådet; Eesti Teadusagentuur; Amsterdam University Medical Centers; Open Philanthropy Project","keywords":"Interpretability; Leverage (statistics); Statistical power; Inference; Predictive power; Confounding; Computer science; Causal inference; Phenotype; Statistics; Data mining; Computational biology; Biology; Machine learning; Mathematics; Artificial intelligence; Genetics","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":[0.02108211,0.001559545,0.002143664,0.007139023,0.0008406734,0.004631377,0.00495285,0.001584171,0.02457354],"category_scores_gemma":[0.09745066,0.001605118,0.001852032,0.01057067,0.0006256162,0.003168371,0.004864175,0.003673863,0.008630871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009312136,"about_ca_system_score_gemma":0.004943452,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005790524,"about_ca_topic_score_gemma":0.009392244,"domain_scores_codex":[0.9915902,0.002896337,0.001306697,0.001620745,0.002322297,0.000263746],"domain_scores_gemma":[0.9200959,0.03130749,0.003661913,0.03513385,0.007086881,0.002713964],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001155334,0.000210857,0.05830225,0.001551899,0.001762234,0.0006114333,0.0004736258,0.0103592,0.00274051,0.0213277,0.6340079,0.2674971],"study_design_scores_gemma":[0.002168832,0.0003843324,0.07061154,0.001187739,0.001909226,0.002136102,0.0001394008,0.03411537,0.005817316,0.09244066,0.7885934,0.0004961522],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.01718883,0.002611066,0.2699564,0.00509598,0.001716967,0.0005869141,0.6579537,0.03699434,0.007895812],"genre_scores_gemma":[0.04186055,0.002139038,0.2392382,0.001763242,0.001159208,0.001638249,0.6996668,0.007364783,0.005170017],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.02457354,"threshold_uncertainty_score":0.1114942,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008800072691724229,"score_gpt":0.2432007580740181,"score_spread":0.2344006853822938,"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."}}