{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001307986,0.0002066447,0.0002199825,0.0001525778,0.0001790085,0.0001287088,0.0003647217,0.0001115161,0.00001014086],"category_scores_gemma":[0.00001667173,0.000197881,0.00002954408,0.00006998641,0.00007281196,0.001003373,0.0003887145,0.0002926692,0.00002405105],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002433862,"about_ca_system_score_gemma":0.0001171785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005294844,"about_ca_topic_score_gemma":0.00001134049,"domain_scores_codex":[0.9989877,0.00000379973,0.0004739126,0.0002208581,0.0001608723,0.0001528392],"domain_scores_gemma":[0.9988899,0.00003435674,0.0004288423,0.0003496719,0.0002125087,0.00008471072],"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":[0.000001736109,0.00001297361,6.180982e-7,0.0002590581,0.000004127014,9.942451e-8,0.0007036579,0.00003487857,0.0002727648,0.007396518,0.00003385625,0.9912797],"study_design_scores_gemma":[0.0005108418,0.00005201556,0.00001775689,0.001035809,0.0000189027,0.00001572936,0.0001439743,0.7010078,0.002716833,0.0003940767,0.2935588,0.0005274262],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001643302,0.0005092712,0.9539686,0.00003445837,0.0001462998,0.0001526394,0.0001385645,0.00008849154,0.04479732],"genre_scores_gemma":[0.3060964,0.0008274341,0.669933,0.0006932826,0.0002934897,0.0001802742,0.002771067,0.000130125,0.01907495],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9907523,"threshold_uncertainty_score":0.8069353,"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."}}