{"id":"W2082021920","doi":"10.1023/b:mach.0000033118.09057.80","title":"Subquadratic Approximation Algorithms for Clustering Problems in High Dimensional Spaces","year":2004,"lang":"en","type":"article","venue":"Machine Learning","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Cluster analysis; Dimension (graph theory); Clustering high-dimensional data; CURE data clustering algorithm; Mathematics; Quadratic equation; Correlation clustering; Computer science; Constrained clustering; Approximation algorithm; Data stream clustering; Algorithm; Data mining; Pattern recognition (psychology); Artificial intelligence; Combinatorics","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":[0.0004997632,0.0001346701,0.0001488478,0.0001793164,0.000152294,0.0002756951,0.000380256,0.00003256934,0.00000616912],"category_scores_gemma":[0.00005292562,0.0001247398,0.00003555241,0.0003142975,0.00001519014,0.0008152864,0.0002832871,0.0001551667,0.00001694449],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005531347,"about_ca_system_score_gemma":0.00001718881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002669287,"about_ca_topic_score_gemma":0.0001226662,"domain_scores_codex":[0.9989007,0.00003958925,0.0002173884,0.0003511005,0.0002131894,0.0002780099],"domain_scores_gemma":[0.9995952,0.00004902403,0.00009678408,0.0001957501,0.00002399807,0.00003922371],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006529788,0.0001140486,0.002574679,0.0001537114,0.00001823229,0.00001288461,0.0009861514,0.8627483,0.0003588387,0.02110994,0.00003095822,0.1118857],"study_design_scores_gemma":[0.00106828,0.0001024927,0.001514446,0.00006056443,0.00000372368,0.000003952715,0.00001665532,0.9890949,0.00009220606,0.00701273,0.0008572849,0.0001728156],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02024663,0.00007095338,0.9773334,0.001431164,0.0002120508,0.0003871707,0.000002160554,0.0001659303,0.0001505012],"genre_scores_gemma":[0.6578388,0.000005513626,0.341316,0.0001270463,0.00008512108,0.00007808422,0.000112166,0.00001701835,0.0004202437],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6375921,"threshold_uncertainty_score":0.508674,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01808675924643977,"score_gpt":0.2449075163954729,"score_spread":0.2268207571490332,"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."}}