{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008874523,0.0003728049,0.0003777349,0.0001922239,0.0001408025,0.0008433542,0.002781173,0.0001668437,0.00004163033],"category_scores_gemma":[0.000008159327,0.000247924,0.00008334611,0.0007908661,0.00006353046,0.002077796,0.001668599,0.0004427322,0.00003156481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003331041,"about_ca_system_score_gemma":0.000179802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003576722,"about_ca_topic_score_gemma":0.00004139336,"domain_scores_codex":[0.9970408,0.000147539,0.0003213478,0.001469803,0.0004720832,0.0005483974],"domain_scores_gemma":[0.9970382,0.0001183924,0.00005115727,0.002531978,0.00005142614,0.0002088764],"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":[0.00002864579,0.0001937224,0.000003304354,0.0004857978,0.000308132,0.0002442621,0.003000384,0.001647069,0.0003194525,0.6586811,0.03655649,0.2985316],"study_design_scores_gemma":[0.0002390974,0.00006429607,0.000002295043,0.00008652076,0.0000410547,0.0001558758,0.00004817395,0.9687923,0.0001609419,0.01139709,0.0186076,0.0004047602],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00008077863,0.002037324,0.9089099,0.001549733,0.0002862132,0.0002936689,0.00003610845,0.0007351298,0.08607119],"genre_scores_gemma":[0.07253074,0.00006619169,0.9218531,0.0006184356,0.0001892736,0.00002974964,0.00004075889,0.0000513796,0.004620317],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9671453,"threshold_uncertainty_score":0.9999973,"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."}}