{"id":"W2136663225","doi":"10.1007/11424918_30","title":"Comparing Dimension Reduction Techniques for Document Clustering","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Cluster analysis; Computer science; Random projection; Dimensionality reduction; Dimension (graph theory); Projection (relational algebra); Pattern recognition (psychology); Document clustering; Projection pursuit; Clustering high-dimensional data; Data mining; Artificial intelligence; Benchmark (surveying); Reduction (mathematics); Algorithm; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004187403,0.001260924,0.001669147,0.004257606,0.001046004,0.002208689,0.001492687,0.001299517,0.00327196],"category_scores_gemma":[0.01784362,0.0004719963,0.001582591,0.005205421,0.0006267596,0.003385897,0.001643572,0.001247796,0.001414431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001110571,"about_ca_system_score_gemma":0.001020826,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005760623,"about_ca_topic_score_gemma":0.006564576,"domain_scores_codex":[0.9958448,0.001572551,0.0003102942,0.0003984247,0.001632377,0.0002415537],"domain_scores_gemma":[0.9815865,0.0131081,0.0003025925,0.002238437,0.002564377,0.0001999246],"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":[0.00263858,0.0003637597,0.002079918,0.0005338576,0.0005469134,0.00004351792,0.0003194821,0.06756013,0.007838436,0.006391355,0.01286068,0.8988235],"study_design_scores_gemma":[0.0004761044,0.001114378,0.01020426,0.0001202196,0.0006636102,0.0004125144,0.000888922,0.9204082,0.0262902,0.02857414,0.01066749,0.0001799609],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2301123,0.01791194,0.7311521,0.0009717226,0.0009625656,0.0003798392,0.001652412,0.00521721,0.01163989],"genre_scores_gemma":[0.2586778,0.004187467,0.725045,0.0001491181,0.0003140479,0.0002416385,0.004215157,0.0006307009,0.006539047],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005760623,"threshold_uncertainty_score":0.02214539,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02446417511934901,"score_gpt":0.2835790974457323,"score_spread":0.2591149223263833,"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."}}