{"id":"W2309226206","doi":"","title":"Scalable clustering of categorical data and applications","year":2004,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Cluster analysis; Data mining; Categorical variable; Tuple; Redundancy (engineering); Scalability; Constrained clustering; Correlation clustering; Canopy clustering algorithm; Artificial intelligence; Machine learning; Database; Mathematics","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":[0.00008773788,0.00003090667,0.00004390664,0.00002752881,0.00003063337,0.00005929433,0.0008114195,0.000008335996,0.000004313978],"category_scores_gemma":[0.000002679507,0.00002615773,0.000004015584,0.0001539871,0.00001848637,0.0005703923,0.001379437,0.00001888626,0.00001500839],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004156374,"about_ca_system_score_gemma":0.000008651914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006809925,"about_ca_topic_score_gemma":0.00001216709,"domain_scores_codex":[0.9996057,0.000002539324,0.0000727835,0.0001816432,0.0000684778,0.00006892899],"domain_scores_gemma":[0.9992931,0.000007973427,0.00001690864,0.0006467766,0.000009254481,0.00002601442],"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":[4.897038e-7,0.00007107322,0.0001729029,0.00002835665,0.000009992651,0.000002090466,0.00004314585,0.0001781778,0.0001009048,0.747401,0.001297639,0.2506942],"study_design_scores_gemma":[0.0008993115,0.00005939311,0.002049979,0.0000113845,0.00001592158,0.00001727812,0.00007597094,0.7847677,0.0008689868,0.06292958,0.1480052,0.000299252],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00006296956,0.00003457033,0.9920889,0.0004948034,0.00002227277,0.00006872332,0.000003601408,0.00004108902,0.007183047],"genre_scores_gemma":[0.2731267,0.00007203003,0.7255021,0.0002045961,0.00006310223,0.00001343149,0.00005006268,0.000004509147,0.0009634987],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7845895,"threshold_uncertainty_score":0.171937,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03283988717391283,"score_gpt":0.2669851235728413,"score_spread":0.2341452363989284,"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."}}