{"id":"W2028936054","doi":"10.1007/s101150050009","title":"An Index Structure for Data Mining and Clustering","year":2000,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Fudan University; National Science Foundation","keywords":"Cluster analysis; Euclidean distance; Data mining; Computer science; Metric (unit); Set (abstract data type); Index (typography); Visualization; Mathematics; Data set; Computation; Approximation error; Algorithm; Pattern recognition (psychology); Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002313983,0.00007206283,0.0000865042,0.00007765849,0.0001277901,0.0007807057,0.0004406526,0.00003223692,0.000004268629],"category_scores_gemma":[0.000005458377,0.0000619935,0.000005084823,0.00009635787,0.00001132945,0.01070403,0.0001905323,0.00002317434,0.000007243217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005090786,"about_ca_system_score_gemma":0.000009659576,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001009094,"about_ca_topic_score_gemma":0.000009649344,"domain_scores_codex":[0.9994803,0.00001379266,0.0001943678,0.0001352727,0.0000675955,0.0001086791],"domain_scores_gemma":[0.9994371,0.00001719776,0.0000503524,0.0004099534,0.00003451353,0.00005087244],"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":[0.000003149779,0.00000375494,0.0002432576,0.0001533647,0.000007670604,1.170747e-7,0.00213129,0.00003450355,0.000003089254,0.00203041,0.003443012,0.9919464],"study_design_scores_gemma":[0.0002194739,0.00002227217,0.0004670079,0.00001968564,0.000002136306,0.000006005112,0.0001595405,0.7034905,0.00000193404,0.00001184623,0.2955329,0.00006676715],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02200378,0.0005894785,0.9631935,0.00006924679,0.0006421484,0.0005528611,0.000143457,0.0001545539,0.01265095],"genre_scores_gemma":[0.9863914,0.00007617244,0.01219571,0.0001198037,0.0002123818,0.00001528633,0.0004810638,0.000004885491,0.0005032803],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9918796,"threshold_uncertainty_score":0.7760165,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02296360961186923,"score_gpt":0.2681822105133437,"score_spread":0.2452186009014745,"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."}}