{"id":"W2005934890","doi":"10.1007/s10618-013-0336-8","title":"Clustering categorical data in projected spaces","year":2013,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Cluster analysis; Categorical variable; Computer science; Data mining; Outlier; CURE data clustering algorithm; Curse of dimensionality; Clustering high-dimensional data; Correlation clustering; Canopy clustering algorithm; Data stream clustering; Anomaly detection; Probabilistic logic; Set (abstract data type); Artificial intelligence; Pattern recognition (psychology); 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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0005122537,0.0001767185,0.0002208383,0.0001952804,0.0001108705,0.0009675179,0.003463923,0.00006333683,0.000004899204],"category_scores_gemma":[0.0003724272,0.0001553439,0.000009682387,0.0005685687,0.00008873466,0.006134995,0.01219033,0.000210252,0.00004977625],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000418934,"about_ca_system_score_gemma":0.0001606193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000526931,"about_ca_topic_score_gemma":0.0004565036,"domain_scores_codex":[0.9978982,0.0001043619,0.0002557066,0.001050292,0.0002115408,0.0004798602],"domain_scores_gemma":[0.9967571,0.000270487,0.00005224418,0.00275922,0.00004755203,0.0001133555],"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":[0.00001872798,0.0003267635,0.01046154,0.0002790178,0.00004683584,0.0001243381,0.0052985,0.00004942426,0.0009059219,0.0004657592,0.01116628,0.9708569],"study_design_scores_gemma":[0.0004146663,0.00003830996,0.007239657,0.00008294683,0.000003119412,0.0000314366,0.0006492968,0.9885409,0.00003809048,0.0001078749,0.002586714,0.0002669639],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1960435,0.002426523,0.796412,0.0007916735,0.0006971049,0.0006473433,0.0002191654,0.0002804956,0.002482201],"genre_scores_gemma":[0.8464171,0.0002059816,0.1501208,0.00004638406,0.0002465241,0.00005831898,0.0008249712,0.00003468962,0.002045239],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9884915,"threshold_uncertainty_score":0.9957989,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09257415986957443,"score_gpt":0.3536923389834265,"score_spread":0.261118179113852,"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."}}