{"id":"W4249787917","doi":"10.1007/978-1-84996-044-1_6","title":"Efficient Clustering of Databases Induced by Local Patterns","year":2010,"lang":"en","type":"book-chapter","venue":"Advanced information and knowledge processing","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Data mining; Computer science; Coding (social sciences); Similarity measure; Data stream clustering; Similarity (geometry); CURE data clustering algorithm; Database; Correlation clustering; Fuzzy clustering; Artificial intelligence; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007366643,0.0006066138,0.001498919,0.002456033,0.0008660871,0.001981258,0.002432972,0.0007208992,0.00171921],"category_scores_gemma":[0.004869312,0.0006029673,0.001059965,0.005440297,0.0005491981,0.002112709,0.002291084,0.0008832117,0.001300508],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007155201,"about_ca_system_score_gemma":0.001008233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001943825,"about_ca_topic_score_gemma":0.003838934,"domain_scores_codex":[0.9986674,0.0002510352,0.0001111884,0.0004056308,0.0004475758,0.000117121],"domain_scores_gemma":[0.9975439,0.0007273547,0.0002027821,0.0009245791,0.000502819,0.0000986076],"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":[0.0005200857,0.0002166571,0.003676605,0.0006276118,0.0002414969,0.0002277971,0.000431832,0.09315597,0.02869832,0.02272044,0.01408471,0.8353985],"study_design_scores_gemma":[0.0000630839,0.0001624181,0.002717179,0.00005961908,0.0001238385,0.0005993281,0.0003785027,0.8916405,0.01913116,0.07549377,0.009598909,0.00003167233],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03376066,0.000592137,0.9616225,0.0001615774,0.00004310697,0.0001533167,0.0007012296,0.001361267,0.001604248],"genre_scores_gemma":[0.2490731,0.000727523,0.7400106,0.00009880342,0.00007250741,0.0002608056,0.005517838,0.000303144,0.003935682],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002456033,"threshold_uncertainty_score":0.005751312,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.017433731183946,"score_gpt":0.2692690324236701,"score_spread":0.2518353012397241,"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."}}