{"id":"W2278925444","doi":"10.7939/r3b23s","title":"A Synthetic Data Generator for Clustering and Outlier Analysis","year":2006,"lang":"en","type":"article","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":68,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Cluster analysis; Outlier; Data mining; Anomaly detection; Generator (circuit theory); Pattern recognition (psychology); Artificial intelligence","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":[0.00009915296,0.00004287372,0.00006595371,0.00006867352,0.00009251308,0.0001172507,0.000350167,0.00001869728,0.00001004816],"category_scores_gemma":[0.000003480194,0.00003670557,0.00002495905,0.0002679691,0.00001151737,0.0001597694,0.0002373211,0.00001511865,0.000002211171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005452948,"about_ca_system_score_gemma":0.000005584886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008218901,"about_ca_topic_score_gemma":0.0001134086,"domain_scores_codex":[0.9995072,0.000004828203,0.00009248498,0.0002783233,0.00004045273,0.0000767298],"domain_scores_gemma":[0.9992637,0.00002062348,0.00002450856,0.0006467348,0.00002288579,0.00002156356],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008166076,0.0002728447,0.003078938,0.00005011641,0.000409412,0.000002506565,0.0001179836,0.001497497,0.01551597,0.6163901,0.0589418,0.3037147],"study_design_scores_gemma":[0.00003908676,0.000009380594,0.0006338111,5.500191e-7,0.00003669598,0.000002017794,0.00000278695,0.9741563,0.001949801,0.001466547,0.02163765,0.00006534775],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001844328,0.00002862824,0.9962173,0.0004041946,0.00001068011,0.0001071804,0.000009619762,0.0001610016,0.001217115],"genre_scores_gemma":[0.6091137,0.000002943941,0.3899019,0.00009100654,0.00002749259,0.00004066046,0.000007411541,0.000002486834,0.0008124268],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9726588,"threshold_uncertainty_score":0.149681,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02587532111683141,"score_gpt":0.2705733718957009,"score_spread":0.2446980507788695,"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."}}