{"id":"W1891514807","doi":"10.1007/3-540-47887-6_4","title":"On Data Clustering Analysis: Scalability, Constraints, and Validation","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Computer science; Scalability; Data mining; Correlation clustering; Similarity (geometry); Consensus clustering; CURE data clustering algorithm; Artificial intelligence; Machine learning; Database","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":[0.09286975,0.003180394,0.00496768,0.005025295,0.00366681,0.007899754,0.008711525,0.005999687,0.003603831],"category_scores_gemma":[0.3498641,0.002624653,0.003295851,0.009786966,0.00758834,0.02164654,0.01261559,0.007990186,0.001515226],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004350682,"about_ca_system_score_gemma":0.008509657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01005519,"about_ca_topic_score_gemma":0.009102168,"domain_scores_codex":[0.9064413,0.05417688,0.006022006,0.006326301,0.02502504,0.00200856],"domain_scores_gemma":[0.5357109,0.3510808,0.008944332,0.06862209,0.03327026,0.00237163],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001767132,0.0006070916,0.01816363,0.001301904,0.0007371357,0.00031021,0.0009414972,0.2598436,0.005876109,0.1025189,0.01982845,0.5881044],"study_design_scores_gemma":[0.0001069672,0.00009245071,0.001267191,0.0001977312,0.00009199145,0.000226076,0.0001577269,0.8876345,0.003979114,0.1044671,0.00172984,0.00004937829],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01546109,0.002090272,0.9720865,0.002543507,0.0001700555,0.000554643,0.0003631346,0.00284984,0.003880897],"genre_scores_gemma":[0.1610958,0.001342199,0.8317899,0.0008916941,0.000411779,0.0007241092,0.001038828,0.001037214,0.001668363],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.09286975,"threshold_uncertainty_score":0.4911481,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05015855301203107,"score_gpt":0.3133047514182548,"score_spread":0.2631461984062237,"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."}}