{"id":"W4394998074","doi":"10.21203/rs.3.rs-4266384/v1","title":"Assessing Model Validity Using KL Divergence and Beta-Stacy Process for Right Censored Data","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Divergence (linguistics); Process (computing); BETA (programming language); Econometrics; Statistics; Computer science; Mathematics; Programming language; Philosophy; Linguistics","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":[0.146905,0.001575124,0.002540823,0.00649016,0.002210502,0.006284286,0.003622709,0.003351156,0.002836241],"category_scores_gemma":[0.5862327,0.0008876472,0.003607228,0.003898267,0.007830731,0.009276073,0.006373619,0.00560482,0.0003865326],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002596848,"about_ca_system_score_gemma":0.005938904,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004640903,"about_ca_topic_score_gemma":0.002776039,"domain_scores_codex":[0.8764241,0.0903311,0.006740957,0.008890819,0.01621734,0.001395756],"domain_scores_gemma":[0.2380332,0.7092459,0.01198682,0.02759926,0.01129289,0.001841963],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001863302,0.0009018165,0.1778507,0.001421536,0.004864659,0.0007050244,0.004765025,0.356489,0.002350245,0.2639574,0.003924202,0.180907],"study_design_scores_gemma":[0.0001172328,0.0004770204,0.01186727,0.0002426571,0.0001908908,0.0002215032,0.0008293096,0.742546,0.001037028,0.241655,0.000737765,0.00007841965],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1883405,0.0006006433,0.8070722,0.0008358132,0.00009935944,0.0002228744,0.0002718646,0.0003142199,0.002242571],"genre_scores_gemma":[0.8459725,0.0002474863,0.1517798,0.0002362556,0.00008394513,0.0003714015,0.000706586,0.0001757958,0.0004263191],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.146905,"threshold_uncertainty_score":0.7769171,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7761963905194896,"score_gpt":0.6333939167535847,"score_spread":0.1428024737659049,"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."}}