{"id":"W4383913721","doi":"10.1111/coin.12593","title":"Online short text clustering using infinite extensions of discrete mixture models","year":2023,"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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Dirichlet distribution; Computer science; Multinomial distribution; Gibbs sampling; Prior probability; Artificial intelligence; Latent Dirichlet allocation; Benchmark (surveying); Outlier; Topic model; Pattern recognition (psychology); Machine learning; Mathematics; Statistics; Bayesian probability","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":[],"consensus_categories":[],"category_scores_codex":[0.0003676263,0.0001831007,0.0002523799,0.0002754071,0.0001360049,0.00006395503,0.0007174131,0.00008367057,0.000008270063],"category_scores_gemma":[0.00006579962,0.000171008,0.0001172329,0.001127163,0.00009420593,0.0004508439,0.0005116712,0.000194519,0.00001532642],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002787976,"about_ca_system_score_gemma":0.0001159836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001881549,"about_ca_topic_score_gemma":0.000005813669,"domain_scores_codex":[0.9983098,0.00009523718,0.0004756332,0.0004390031,0.0003935693,0.0002867593],"domain_scores_gemma":[0.9986733,0.0004054703,0.0001027302,0.0003945017,0.0003090394,0.0001149659],"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":[0.00000349859,0.00003003179,0.00002291414,0.00002000276,0.00001467721,0.00001038743,0.0004973973,0.8716409,0.0003853905,0.08060743,0.00006341033,0.04670398],"study_design_scores_gemma":[0.00002357846,0.00002164871,0.0003683138,0.00007522824,0.000005861786,0.00002552891,0.00002402656,0.7529106,0.0003773557,0.2459962,0.00003091032,0.0001407688],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009354228,0.0001443364,0.9892987,0.000294034,0.0003125132,0.0001431508,0.00002715995,0.000161898,0.0002639604],"genre_scores_gemma":[0.4732709,0.00002635485,0.5264531,0.000127525,0.00004129968,0.000002696358,0.00001899418,0.00001017992,0.00004900468],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4639166,"threshold_uncertainty_score":0.6973505,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1131347818749508,"score_gpt":0.3644947936831115,"score_spread":0.2513600118081607,"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."}}