{"id":"W4220966911","doi":"10.1145/3502727","title":"Stochastic Variational Optimization of a Hierarchical Dirichlet Process Latent Beta-Liouville Topic Model","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Latent Dirichlet allocation; Dirichlet process; Hierarchical Dirichlet process; Topic model; Computer science; Measure (data warehouse); Dirichlet distribution; Inference; Prior probability; Parametric statistics; Bayesian inference; Posterior probability; Mathematics; Bayesian probability; Applied mathematics; Artificial intelligence; Data mining; 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":[0.0003895146,0.0001792017,0.0002581106,0.0001827246,0.0003898547,0.00008887001,0.002619837,0.00005751662,0.0001254563],"category_scores_gemma":[0.00004735011,0.0001774103,0.00008688738,0.0005522099,0.00004750236,0.001113881,0.0002850353,0.0004107635,0.000004564876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000690711,"about_ca_system_score_gemma":0.0003559192,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002774527,"about_ca_topic_score_gemma":0.00001335641,"domain_scores_codex":[0.9980469,0.0002525247,0.0003601518,0.0007135252,0.0004115695,0.00021531],"domain_scores_gemma":[0.9974003,0.0003598307,0.0001157108,0.001965271,0.00007810251,0.00008071945],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004676621,0.0007779908,0.000006229852,0.00001696267,0.00008472484,0.000001549354,0.00111712,0.9653277,0.0000610475,0.01323663,0.0001918596,0.01913139],"study_design_scores_gemma":[0.0004508341,0.00007737064,0.00006011016,0.0000161612,0.00005949457,0.000003567656,0.00001903762,0.9572123,0.0001174792,0.04174845,0.00005026381,0.0001849586],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007537141,0.0001397633,0.9948135,0.0007832203,0.0004282722,0.0002509056,0.00258155,0.00005919693,0.0001898567],"genre_scores_gemma":[0.5385419,0.00001192953,0.4602747,0.0001076336,0.00004253527,0.00009208557,0.0006249801,0.00001666074,0.0002876177],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5377881,"threshold_uncertainty_score":0.7234583,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04890874881870901,"score_gpt":0.3044790594634345,"score_spread":0.2555703106447255,"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."}}