{"id":"W2089055054","doi":"10.1145/1401890.1401956","title":"Finding non-redundant, statistically significant regions in high dimensional data","year":2008,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":109,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Disjoint sets; Computer science; Cluster (spacecraft); Outlier; Data mining; Single-linkage clustering; Clustering high-dimensional data; Subspace topology; Complete-linkage clustering; Data point; Correlation clustering; Determining the number of clusters in a data set; CURE data clustering algorithm; Pattern recognition (psychology); Artificial intelligence; Mathematics; Combinatorics","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":[0.0003107999,0.0001271416,0.0001712153,0.0001754543,0.0001912596,0.00005962105,0.001887831,0.00004190151,0.00004308532],"category_scores_gemma":[0.0002266414,0.0001134627,0.00001575646,0.0005454281,0.000148681,0.0006289182,0.001916132,0.0002620393,0.0001214472],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008419678,"about_ca_system_score_gemma":0.0002575786,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000312938,"about_ca_topic_score_gemma":0.00004386804,"domain_scores_codex":[0.9979486,0.00005902998,0.0002691845,0.0006784492,0.0005536832,0.0004910497],"domain_scores_gemma":[0.9979619,0.0004239273,0.00003965025,0.001338189,0.00006814266,0.0001681949],"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":[0.0001859811,0.002341949,0.008631247,0.000161801,0.0001694143,0.01974997,0.003218761,0.0560712,0.02791096,0.541252,0.1038724,0.2364343],"study_design_scores_gemma":[0.0005204628,0.00007631245,0.01849069,0.00002964708,0.000001093695,0.0001300865,0.00001297317,0.9751111,0.0003769333,0.004364144,0.0006429841,0.0002435287],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0119481,0.0000101387,0.9857756,0.001253216,0.0001435971,0.0001472607,0.00002665894,0.00009735882,0.0005980128],"genre_scores_gemma":[0.4299299,0.00001654303,0.5685577,0.0001134737,0.00003267332,0.000009066357,0.00002646466,0.000009960856,0.001304283],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.91904,"threshold_uncertainty_score":0.4626873,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1047099670015588,"score_gpt":0.3439923630461722,"score_spread":0.2392823960446134,"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."}}