{"id":"W1560541823","doi":"10.1007/978-3-540-24741-8_9","title":"LIMBO: Scalable Clustering of Categorical Data","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":260,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Categorical variable; Cluster analysis; Computer science; Data mining; Tuple; Data stream clustering; Hierarchical clustering; Bottleneck; Scalability; Measure (data warehouse); CURE data clustering algorithm; Correlation clustering; Clustering high-dimensional data; Artificial intelligence; Machine learning; Database; 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":[0.001481647,0.00144688,0.002048129,0.003256861,0.001583504,0.002625802,0.004145035,0.0009237397,0.01694855],"category_scores_gemma":[0.006111883,0.001379541,0.002395253,0.006372483,0.000685823,0.002928334,0.004924891,0.002147383,0.01129535],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001009359,"about_ca_system_score_gemma":0.002159623,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0073229,"about_ca_topic_score_gemma":0.01413778,"domain_scores_codex":[0.9983224,0.0003099332,0.0001215514,0.000272689,0.0008174219,0.000155941],"domain_scores_gemma":[0.9978982,0.0004453268,0.00009649377,0.0009617906,0.000429305,0.0001689065],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006807392,0.0002201192,0.001464615,0.0006858487,0.000254577,0.0001931238,0.0002366523,0.02278141,0.01076154,0.01564228,0.2437471,0.7033319],"study_design_scores_gemma":[0.0004898231,0.0002014556,0.002855616,0.0001521482,0.0001868822,0.0005725932,0.0002563499,0.7180532,0.01863345,0.1480262,0.1104236,0.0001486605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004928685,0.0005555298,0.9234459,0.000268353,0.0002638773,0.0002975948,0.005706437,0.06098786,0.003545901],"genre_scores_gemma":[0.0305278,0.0003678072,0.9360351,0.0002391435,0.00009973413,0.0006086082,0.02082241,0.003933636,0.007365793],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01694855,"threshold_uncertainty_score":0.05669856,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04748493022922919,"score_gpt":0.3097387021538155,"score_spread":0.2622537719245863,"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."}}