{"id":"W2965409371","doi":"10.1109/isie.2019.8781307","title":"Model-Based Hierarchical Clustering for Categorical Data","year":2019,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Cluster analysis; Bhattacharyya distance; Categorical variable; Computer science; Hierarchical clustering; Brown clustering; Artificial intelligence; Multinomial distribution; Binary data; Data mining; Pattern recognition (psychology); Fuzzy clustering; Consensus clustering; Mixture model; CURE data clustering algorithm; Machine learning; Binary number; Mathematics; Statistics","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":[0.0004819426,0.0001003078,0.0001498699,0.00004614517,0.00004689946,0.00009595867,0.001602706,0.00006542608,0.00001239589],"category_scores_gemma":[0.00002463309,0.00007804902,0.00004643414,0.0001059458,0.00001402323,0.0003147005,0.0005660064,0.0001059967,0.00002445104],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001527589,"about_ca_system_score_gemma":0.0001084823,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005908762,"about_ca_topic_score_gemma":0.000004538135,"domain_scores_codex":[0.9988781,0.00003871997,0.0001473362,0.0005314077,0.000142349,0.0002620372],"domain_scores_gemma":[0.9982717,0.0001567308,0.00002462744,0.001412376,0.00003147661,0.0001030732],"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":[0.00001824865,0.00005227148,0.00002373983,0.0000378031,0.000007662271,0.000002004373,0.00005714629,0.004141007,0.0008925791,0.8300584,0.003292044,0.1614171],"study_design_scores_gemma":[0.0003166241,0.00003843349,0.000008127345,0.000002699775,0.000002551017,0.000002802376,4.365924e-7,0.9194933,0.00019574,0.07763286,0.002190167,0.0001162861],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001326069,0.00001653077,0.9927541,0.001895524,0.000243474,0.0002569314,0.000005467768,0.0001215665,0.004573779],"genre_scores_gemma":[0.1646374,6.867436e-7,0.8331155,0.001208357,0.00004559303,0.000009933866,0.00001079325,0.000008100877,0.0009636372],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9153523,"threshold_uncertainty_score":0.3182747,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07657443905414395,"score_gpt":0.3270737095638069,"score_spread":0.250499270509663,"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."}}