{"id":"W2164582339","doi":"10.1109/ijcnn.2006.247041","title":"PARTCAT: A Subspace Clustering Algorithm for High Dimensional Categorical Data","year":2006,"lang":"en","type":"article","venue":"The 2006 IEEE International Joint Conference on Neural Network Proceedings","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Categorical variable; Cluster analysis; Computer science; Subspace topology; Data mining; Dimension (graph theory); Similarity (geometry); Clustering high-dimensional data; Artificial intelligence; Artificial neural network; Cluster (spacecraft); Pattern recognition (psychology); Algorithm; Mathematics; Machine learning","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":[0.0007108852,0.0003733914,0.0003213585,0.0001308488,0.0004203636,0.0006787482,0.003596549,0.0001050402,0.00002325931],"category_scores_gemma":[0.00007272784,0.0002846633,0.00009378949,0.000407973,0.000168701,0.0009756375,0.001327827,0.0005292122,0.00005376637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001695146,"about_ca_system_score_gemma":0.00009322597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001703798,"about_ca_topic_score_gemma":0.0000369478,"domain_scores_codex":[0.9964405,0.00003567445,0.0005390928,0.001045252,0.001090046,0.0008493939],"domain_scores_gemma":[0.9979443,0.0002657383,0.0002870699,0.0006574048,0.000706267,0.000139233],"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":[0.0003627862,0.000545853,0.0001897612,0.00006492181,0.0002300941,0.00008751153,0.000254928,0.1623174,0.004513971,0.3456495,0.1495404,0.3362429],"study_design_scores_gemma":[0.0005895165,0.0001574479,0.0005353718,0.00005592874,0.000009000386,0.0001220538,0.00001054831,0.9707219,0.0005703593,0.02496225,0.001937191,0.000328402],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007330746,0.00004794984,0.9684795,0.0187403,0.002694737,0.0008139866,0.00008755919,0.0003637548,0.001441506],"genre_scores_gemma":[0.8853487,0.00002516215,0.1077492,0.0007499927,0.003302827,0.0002059801,0.0001237942,0.00005255119,0.002441728],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.878018,"threshold_uncertainty_score":0.9999605,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08700548172302576,"score_gpt":0.3200420799469654,"score_spread":0.2330365982239396,"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."}}