{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007767887,0.001040549,0.001275611,0.002899152,0.001710688,0.00262085,0.002095911,0.001913802,0.009014289],"category_scores_gemma":[0.05017545,0.0009930634,0.002144358,0.003549946,0.001409121,0.003927511,0.002717575,0.004139185,0.003005593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009046394,"about_ca_system_score_gemma":0.003023198,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004233336,"about_ca_topic_score_gemma":0.009080557,"domain_scores_codex":[0.9963487,0.001956733,0.000220544,0.0009555095,0.0003675598,0.0001508129],"domain_scores_gemma":[0.9794223,0.01525419,0.0007820398,0.003586755,0.0007300488,0.0002246457],"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":[0.0007952666,0.0002881207,0.04596576,0.001114634,0.001202126,0.0008009216,0.002732716,0.1910852,0.006110254,0.2204796,0.0522759,0.4771495],"study_design_scores_gemma":[0.00007737158,0.00003089854,0.002223036,0.0001174248,0.000128673,0.0002473441,0.0002038104,0.6726657,0.002834639,0.3053751,0.01603319,0.00006280896],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01342452,0.0004104485,0.9762312,0.0005328468,0.000125772,0.0001144618,0.003884353,0.003415317,0.001861149],"genre_scores_gemma":[0.2228454,0.0005372555,0.7573134,0.0005724165,0.00025635,0.0005637046,0.01402689,0.001219526,0.00266504],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009014289,"threshold_uncertainty_score":0.04108101,"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."}}