{"id":"W4389042830","doi":"10.1109/isncc58260.2023.10323873","title":"Generalized Probabilistic Clustering Projection Models for Discrete Data","year":2023,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Latent Dirichlet allocation; Cluster analysis; Perplexity; Prior probability; Dirichlet distribution; Projection (relational algebra); Mathematics; Pattern recognition (psychology); Generalized Dirichlet distribution; Computer science; Artificial intelligence; Probabilistic logic; Topic model; Algorithm; Bayesian probability; Dirichlet series; Language model","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":[0.0008196761,0.0001094842,0.0001365905,0.00008659395,0.0001227518,0.0001639481,0.001001016,0.00004847494,0.000002494816],"category_scores_gemma":[0.0000591423,0.00008518383,0.00004205557,0.000383818,0.00001480406,0.0008198668,0.0007529151,0.00005165272,0.000008751467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001829446,"about_ca_system_score_gemma":0.00005074197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000479052,"about_ca_topic_score_gemma":0.00005036629,"domain_scores_codex":[0.9987673,0.00006341746,0.0001833409,0.0005679026,0.0001378319,0.0002802634],"domain_scores_gemma":[0.9986922,0.00008314825,0.00004111352,0.001076887,0.00004785228,0.0000588488],"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":[0.00001440708,0.00001593773,0.000002297854,0.00009041178,0.00001868801,0.000002529863,0.0003713807,0.006270378,0.0007462709,0.8619665,0.008822699,0.1216785],"study_design_scores_gemma":[0.0001822733,0.00002151828,0.000003228515,0.000006771858,0.000004665404,0.000003562062,0.00000272382,0.7226302,0.00008046954,0.2759698,0.0009984839,0.00009627928],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001510631,0.00001587585,0.9958936,0.000995987,0.0003898818,0.00063606,0.00001636266,0.000571995,0.001329204],"genre_scores_gemma":[0.00682015,0.00001329931,0.9901077,0.0001721955,0.0001149799,0.0001300072,0.00005065309,0.0000141259,0.002576925],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7163598,"threshold_uncertainty_score":0.3473696,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1401373378521512,"score_gpt":0.3548434531343582,"score_spread":0.2147061152822071,"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."}}