{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001205164,0.0005360007,0.0007265948,0.0009317759,0.0002067775,0.0003800489,0.01159087,0.0003363326,0.00002770917],"category_scores_gemma":[0.0002157368,0.0005094908,0.00009256483,0.001027056,0.00102307,0.001230497,0.01265155,0.001174847,0.00004592852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006443911,"about_ca_system_score_gemma":0.001318411,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001051044,"about_ca_topic_score_gemma":0.00008379173,"domain_scores_codex":[0.9941866,0.00003491182,0.0007281851,0.002292896,0.00177164,0.0009858136],"domain_scores_gemma":[0.9940843,0.0004851949,0.0003175676,0.004507013,0.0003407173,0.0002651922],"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":[0.000008135601,0.0000479449,0.00001008101,0.0001401343,0.00001441524,0.0002130566,0.0002861826,0.2899748,0.0002000741,0.009538195,0.00001000874,0.6995569],"study_design_scores_gemma":[0.0003047069,0.0001768092,0.00002781117,0.0003663483,0.000004556136,0.0001226205,1.089588e-7,0.8738716,0.0009581893,0.1231642,0.0005002025,0.0005027671],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000009869559,0.0004661749,0.9950686,0.0005129403,0.001207093,0.0003564725,0.00001442922,0.0001526264,0.002211819],"genre_scores_gemma":[0.05062989,0.0001027665,0.9481131,0.0002377613,0.000391141,0.000006198369,0.000015594,0.00005766701,0.0004458115],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6990542,"threshold_uncertainty_score":0.9997357,"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."}}