{"id":"W2974097300","doi":"10.1109/iri.2019.00050","title":"Data Clustering Using Online Variational Learning of Finite Scaled Dirichlet Mixture Models","year":2019,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Cluster analysis; Scalability; Inference; Latent Dirichlet allocation; Data mining; Mixture model; Dirichlet distribution; Topic model; Machine learning; Data modeling; Anomaly detection; Artificial intelligence; Bayesian inference; Bayesian probability; 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":[0.0006291541,0.0001356723,0.000242743,0.0001008269,0.00005813941,0.00006730482,0.001181519,0.0000894058,0.00005182367],"category_scores_gemma":[0.00005652733,0.0001159459,0.00004678711,0.0003016538,0.00001595545,0.0009705455,0.00111981,0.0002157041,0.000006053807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001698663,"about_ca_system_score_gemma":0.00008591789,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003476476,"about_ca_topic_score_gemma":0.000007611751,"domain_scores_codex":[0.9985732,0.0001427343,0.0002996245,0.0004775131,0.0002895533,0.0002173777],"domain_scores_gemma":[0.9985153,0.0002257259,0.0001486967,0.0009466595,0.0001003525,0.00006324473],"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":[0.00002740439,0.0002011843,0.0007116036,0.0001298507,0.0000951661,0.000007645945,0.0008120823,0.6508648,0.01584908,0.2694812,0.00021737,0.06160263],"study_design_scores_gemma":[0.0002712829,0.0000233735,0.0001389797,0.00003870468,0.00000868018,0.00000857281,0.000006310493,0.9854678,0.000105776,0.01345155,0.0003349856,0.0001439653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003805247,0.00007745875,0.9933299,0.0002160948,0.0002267829,0.0001228177,0.00003046776,0.0000713363,0.002119825],"genre_scores_gemma":[0.1584786,0.000007441141,0.8405132,0.0002140908,0.00006612178,5.475443e-7,0.00004513304,0.00001030016,0.0006645242],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.334603,"threshold_uncertainty_score":0.4728136,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06868351113407842,"score_gpt":0.311060159901088,"score_spread":0.2423766487670096,"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."}}