{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001404629,0.0004745574,0.0005004507,0.0009603329,0.0002932014,0.0006839698,0.001969876,0.0003252623,0.000005781655],"category_scores_gemma":[0.00003648274,0.000468175,0.0001442861,0.0003394452,0.0002832251,0.001072812,0.001200714,0.0005933084,0.00000970933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005739374,"about_ca_system_score_gemma":0.0002539447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001522395,"about_ca_topic_score_gemma":0.00005121795,"domain_scores_codex":[0.9967284,0.00003539473,0.0006208092,0.00137845,0.000713844,0.0005230715],"domain_scores_gemma":[0.9979079,0.0001826928,0.0003675729,0.001144912,0.0002791888,0.0001177797],"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":[0.00001149483,0.00002616702,0.000005170756,0.00004340615,0.00000874602,0.000005377433,0.0009808968,0.02195556,0.001372156,0.04282139,0.00008208113,0.9326875],"study_design_scores_gemma":[0.0002777664,0.0003520577,0.00001695071,0.0007345275,0.00001071555,0.000119493,2.792397e-7,0.7430423,0.05859136,0.184457,0.0114288,0.0009687376],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00004890889,0.0001689164,0.993032,0.001307883,0.0008388546,0.001027463,0.000001147895,0.0008161006,0.002758679],"genre_scores_gemma":[0.1167073,0.00004978905,0.8814442,0.0008145588,0.0005220409,0.00005742351,0.000006871438,0.00003797607,0.0003598904],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9317188,"threshold_uncertainty_score":0.999777,"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."}}