{"id":"W1988104581","doi":"10.1007/s00500-012-0972-8","title":"Rough subspace-based clustering ensemble for categorical data","year":2013,"lang":"en","type":"article","venue":"Soft Computing","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Categorical variable; Cluster analysis; Data mining; Linear subspace; Rough set; Pattern recognition (psychology); Computer science; Subspace topology; Clustering high-dimensional data; Artificial intelligence; 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":[],"consensus_categories":[],"category_scores_codex":[0.0004132414,0.0001729221,0.0002111267,0.00005823868,0.0003057784,0.0004633753,0.001847465,0.00007121431,0.000007177016],"category_scores_gemma":[0.0001091065,0.000151833,0.00006128982,0.0002661871,0.00002783874,0.0005034875,0.001087481,0.0001366273,0.00008900295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004029112,"about_ca_system_score_gemma":0.00007681775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000167651,"about_ca_topic_score_gemma":0.00001215492,"domain_scores_codex":[0.9983001,0.00004533466,0.0002702563,0.0006390213,0.0002035341,0.0005417078],"domain_scores_gemma":[0.998096,0.0004246158,0.0001099308,0.001157569,0.00009489533,0.0001170131],"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":[0.00001248138,0.0001995956,0.001881241,0.0001751797,0.00004665952,0.00002735672,0.001019344,0.04476706,0.0006519067,0.01664761,0.03459264,0.8999789],"study_design_scores_gemma":[0.0003608855,0.00005671919,0.0006640183,0.00001425111,0.000004158849,0.000009896553,0.0000172715,0.9905204,0.00007027188,0.003536966,0.004532875,0.0002122445],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004110855,0.0001089349,0.9913793,0.002012124,0.0006012548,0.0003677843,0.000002346099,0.000332198,0.00108521],"genre_scores_gemma":[0.6713228,7.741524e-7,0.3277261,0.0006530483,0.0002253365,0.00000854524,0.0000203756,0.00001245697,0.00003060857],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9457534,"threshold_uncertainty_score":0.6191568,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06700982144290824,"score_gpt":0.2842228375720524,"score_spread":0.2172130161291442,"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."}}