{"id":"W4396244365","doi":"10.48550/arxiv.2404.19528","title":"Tree Pólya Splitting distributions for multivariate count data","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Agence Nationale de la Recherche","keywords":"Multivariate statistics; Tree (set theory); Mathematics; Statistics; Geography; Combinatorics","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","open_science"],"consensus_categories":[],"category_scores_codex":[0.0008676557,0.0003462462,0.000376575,0.0001629929,0.0002337086,0.0003189236,0.003707134,0.0003122656,0.000008376834],"category_scores_gemma":[0.0001214158,0.0003668465,0.0002323901,0.0004608958,0.00007779595,0.0003318414,0.008421073,0.0006587001,0.00004258251],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000166379,"about_ca_system_score_gemma":0.0003177058,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001507851,"about_ca_topic_score_gemma":0.00004913326,"domain_scores_codex":[0.9971767,0.0001414104,0.0002567169,0.00189165,0.00008511821,0.0004483806],"domain_scores_gemma":[0.9962621,0.0002945678,0.0001918105,0.002913195,0.000160395,0.0001778929],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001210697,0.00005501574,0.00001681963,0.0001695504,0.0001275789,0.0001042946,0.0001119314,0.00111501,0.00005063505,0.9814649,0.002514423,0.01425778],"study_design_scores_gemma":[0.00020477,0.00001442874,0.00004881118,0.0001035514,0.0001224942,0.000002892211,0.00000859178,0.6151229,0.0000449237,0.3802625,0.003784469,0.0002797809],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001215043,0.0001841569,0.9924707,0.0005398287,0.001379871,0.0005217697,0.001147759,0.0003586352,0.002182231],"genre_scores_gemma":[0.5910247,0.00008440256,0.4059117,0.00008016491,0.0002734192,0.000004099856,0.0003945924,0.00003185397,0.00219503],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6140078,"threshold_uncertainty_score":0.9998783,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.16697835912166,"score_gpt":0.2588823729926948,"score_spread":0.09190401387103475,"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."}}