{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001473719,0.00047918,0.0005944345,0.001476316,0.0002767109,0.0008942328,0.004985479,0.0002483513,0.00004663227],"category_scores_gemma":[0.0003003922,0.0004573952,0.00007914552,0.001280373,0.001366011,0.0009869543,0.006368254,0.0009094601,0.00003076098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003089427,"about_ca_system_score_gemma":0.0001807532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001513202,"about_ca_topic_score_gemma":0.00004342763,"domain_scores_codex":[0.9947337,0.00006789001,0.0005239446,0.002634657,0.001365127,0.0006746691],"domain_scores_gemma":[0.9948068,0.0009426485,0.0002187642,0.003598001,0.0001992116,0.0002345904],"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":[0.000003564562,0.00002410485,0.00004850675,0.0000386523,0.00004830076,0.00006142483,0.0001913529,0.1299207,0.0000171538,0.00325827,0.000005178348,0.8663828],"study_design_scores_gemma":[0.0001884802,0.0001105055,0.0001526066,0.0001703098,0.00002470471,0.00004702064,1.036904e-7,0.9595024,0.0001190791,0.03912485,0.0001164614,0.0004434672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00007679317,0.0001562616,0.9965968,0.0005485945,0.0004617385,0.0003517018,0.0000261206,0.0001480985,0.001633891],"genre_scores_gemma":[0.2281184,0.0001178483,0.7705205,0.0005433609,0.0002644728,0.000008942415,0.0000380953,0.00004319167,0.0003451783],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8659393,"threshold_uncertainty_score":0.9997878,"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."}}