{"id":"W4394760812","doi":"10.1111/coin.12641","title":"Novel mixture allocation models for topic learning","year":2024,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Latent Dirichlet allocation; Inference; Topic model; Dirichlet distribution; Computer science; Mixture model; Artificial intelligence; Prior probability; Latent variable; Categorization; Machine learning; Pattern recognition (psychology); Mathematics","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":[0.0003571071,0.0001257541,0.0001092405,0.0001112213,0.0001235628,0.0002823822,0.0004446168,0.00006939118,0.000008046264],"category_scores_gemma":[0.00006945063,0.0001175744,0.00009056526,0.0003204473,0.00002844396,0.00052349,0.00007842169,0.0001744837,0.00002599127],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004149958,"about_ca_system_score_gemma":0.000123751,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003830479,"about_ca_topic_score_gemma":7.424368e-7,"domain_scores_codex":[0.9989236,0.00003452373,0.0002233692,0.0004330005,0.0001995972,0.0001859018],"domain_scores_gemma":[0.9988667,0.0006849845,0.00003638898,0.0001571738,0.0001922203,0.00006253179],"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":[0.000001072876,0.000009690267,3.221606e-7,0.00002516454,0.000008188862,9.499326e-7,0.0003479857,0.2489897,0.00008983326,0.5660193,0.0002404291,0.1842673],"study_design_scores_gemma":[0.00001642565,0.00002215742,0.000003606575,0.00002926589,0.000002934919,0.00001325802,0.000004079001,0.5406963,0.0003990819,0.4562629,0.002472203,0.00007779329],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002205692,0.001015452,0.994625,0.001905987,0.0006216994,0.0001988756,0.000003437469,0.0002547659,0.001352681],"genre_scores_gemma":[0.1974168,0.00001720729,0.8007954,0.0003801504,0.0001380843,0.00003928952,0.00001601681,0.00001057952,0.001186464],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2917065,"threshold_uncertainty_score":0.4794544,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05465376630462006,"score_gpt":0.3294408408894598,"score_spread":0.2747870745848398,"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."}}