{"id":"W2612181456","doi":"10.1007/978-1-4899-7502-7_35-1","title":"Categorical Data Clustering","year":2016,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Machine Learning and Data Mining","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Categorical variable; Cluster analysis; Computer science; Data mining; Domain (mathematical analysis); Cluster (spacecraft); Artificial intelligence; Machine learning; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001025443,0.001004287,0.001108012,0.003636122,0.001184596,0.002652238,0.002135462,0.0008306275,0.03074577],"category_scores_gemma":[0.003389126,0.0005975033,0.001263751,0.007035077,0.0005996338,0.001807377,0.002015249,0.001636737,0.03405502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001012899,"about_ca_system_score_gemma":0.001489957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001659734,"about_ca_topic_score_gemma":0.002521211,"domain_scores_codex":[0.9986207,0.0001592823,0.00009331089,0.0003550104,0.0007098349,0.00006170809],"domain_scores_gemma":[0.9985606,0.0002422471,0.00004460322,0.0004559379,0.000631267,0.00006529984],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004035785,0.00004695279,0.0004771482,0.0003436088,0.00004593951,0.0000486726,0.0001248388,0.003715056,0.003381341,0.0517556,0.1509543,0.7890661],"study_design_scores_gemma":[0.00001479949,0.00006364826,0.001880671,0.0002216886,0.00005167303,0.0009043564,0.0001912992,0.05505541,0.009964566,0.1741544,0.7574114,0.00008610731],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001621298,0.004119958,0.9251781,0.000792303,0.0009177334,0.0002614647,0.003672235,0.007820287,0.05561672],"genre_scores_gemma":[0.02261514,0.004992927,0.8799335,0.0006020788,0.0005653283,0.0004184896,0.01586464,0.001457106,0.07355078],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03074577,"threshold_uncertainty_score":0.1028548,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05026195322463737,"score_gpt":0.3275556204352275,"score_spread":0.2772936672105901,"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."}}