{"id":"W4410695830","doi":"10.1101/2025.05.20.655151","title":"Sampling Aware Ancestral State Inference","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Simon Fraser University; Michael Smith Health Research BC; Strong; Public Health Agency; Public Health Agency of Canada","keywords":"Inference; Sampling (signal processing); State (computer science); Computer science; Statistics; Econometrics; Mathematics; Artificial intelligence; Algorithm","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":[0.001527234,0.0003795681,0.000539012,0.0003307169,0.0006094621,0.0004535332,0.0008243858,0.0003399279,0.0001222511],"category_scores_gemma":[0.00078071,0.0004265299,0.0002381287,0.001038156,0.0002497453,0.0001917752,0.0004632934,0.0007166048,0.00003952189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003327432,"about_ca_system_score_gemma":0.002709576,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001508716,"about_ca_topic_score_gemma":0.0001765693,"domain_scores_codex":[0.9969043,0.0004953504,0.0005162887,0.0008525233,0.0006409921,0.0005906114],"domain_scores_gemma":[0.9974131,0.0005170997,0.0003749114,0.0005911444,0.0008282294,0.0002754891],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002952463,0.002106616,0.5226389,0.004810897,0.005006087,0.0004105242,0.004042158,0.08762272,0.06004893,0.3067056,0.003706166,0.002606243],"study_design_scores_gemma":[0.001399651,0.00009503932,0.7340208,0.003470101,0.00104029,4.996381e-9,0.0001699483,0.01186688,0.01821212,0.003364948,0.2205251,0.005835093],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7313005,0.001627447,0.257544,0.001651398,0.004372628,0.001081082,0.0006140952,0.001243888,0.0005650081],"genre_scores_gemma":[0.97258,0.0004212979,0.02600893,0.0001915258,0.000588511,0.0000766146,4.356835e-7,0.00002584961,0.0001068368],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3033406,"threshold_uncertainty_score":0.9998186,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05651519816079217,"score_gpt":0.3516928275629704,"score_spread":0.2951776294021782,"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."}}