{"id":"W2669206880","doi":"10.1080/01621459.2018.1505626","title":"MCMC for Imbalanced Categorical Data","year":2018,"lang":"en","type":"preprint","venue":"Journal of the American Statistical Association","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Categorical variable; Computer science; Markov chain Monte Carlo; Bayesian probability; Approximate Bayesian computation; Computational complexity theory; Computation; Sample size determination; Sample (material); Bayesian inference; Logarithm; Machine learning; Data mining; Algorithm; Artificial intelligence; Mathematics; Statistics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002564289,0.0001827402,0.0006521844,0.0000628395,0.0001102226,0.0002159394,0.003181599,0.0001163697,0.000003875316],"category_scores_gemma":[0.003748517,0.0001195022,0.0001865614,0.0002179973,0.00009684758,0.0001702836,0.001591812,0.0006836356,0.000003598767],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004908936,"about_ca_system_score_gemma":0.0004808868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003314348,"about_ca_topic_score_gemma":0.000004604166,"domain_scores_codex":[0.9973801,0.0005707826,0.0006708507,0.0003670083,0.0007104604,0.0003008171],"domain_scores_gemma":[0.9934195,0.00154324,0.00324972,0.00101669,0.0006470789,0.0001237669],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000179488,0.0003180387,0.003135448,0.0001056108,0.0008172795,0.00001471889,0.0004263587,0.00007693718,0.0002732058,0.1261761,0.5332782,0.3351986],"study_design_scores_gemma":[0.0004808066,0.0003759334,0.02492063,0.00006267231,0.0002879401,0.00002951684,0.000008065786,0.1037633,0.00007183424,0.8581315,0.01153254,0.0003352381],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004678611,0.00004377306,0.9901397,0.006588497,0.002092472,0.0001994749,0.0003308585,0.00001642222,0.0001209336],"genre_scores_gemma":[0.04198985,0.00004674599,0.9557546,0.0008147616,0.001178266,0.000005989661,0.00002065057,0.00001581325,0.0001733686],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7319554,"threshold_uncertainty_score":0.5912256,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03988550071863376,"score_gpt":0.3559444286280251,"score_spread":0.3160589279093913,"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."}}