{"id":"W4401009914","doi":"10.1145/3654522.3654551","title":"Data Clustering with Libby-Novick Beta-Liouville Mixture Models: A Minimum Message Length Approach","year":2024,"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":"Cluster analysis; Computer science; Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009763496,0.001645609,0.00224938,0.003397655,0.001821882,0.003289981,0.005628365,0.003537523,0.002532689],"category_scores_gemma":[0.03193029,0.001639298,0.002051674,0.003279817,0.002239961,0.005002907,0.005162994,0.005096853,0.002660195],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003094222,"about_ca_system_score_gemma":0.002619954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00491045,"about_ca_topic_score_gemma":0.005586457,"domain_scores_codex":[0.9925321,0.004310005,0.0004595638,0.001128334,0.00128345,0.0002866607],"domain_scores_gemma":[0.9846472,0.01001079,0.001228657,0.001933934,0.001780171,0.0003993468],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004786215,0.0001991865,0.003068155,0.0003612387,0.0002620303,0.0002304431,0.0007728306,0.5178255,0.00747584,0.145963,0.00446591,0.3188972],"study_design_scores_gemma":[0.00001143179,0.00002494666,0.0001265726,0.00001787878,0.00001120754,0.00004567057,0.00002490337,0.9590039,0.001496992,0.03773677,0.001475996,0.00002373139],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008208653,0.00006920326,0.9986135,0.00008096153,0.00000973935,0.00002161214,0.00001917299,0.0002615475,0.0001034582],"genre_scores_gemma":[0.04899263,0.0002341544,0.9475614,0.0002815137,0.00009680525,0.0003695054,0.000442189,0.0003468019,0.001675001],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009763496,"threshold_uncertainty_score":0.05163491,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05842989801651446,"score_gpt":0.2816727622763654,"score_spread":0.2232428642598509,"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."}}