{"id":"W2146849021","doi":"10.1109/icdmw.2009.88","title":"Document Clustering Using Semantic Kernels Based on Term-Term Correlations","year":2009,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Term (time); Computer science; Cluster analysis; Artificial intelligence; Information retrieval; Natural language processing; Physics","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":[0.000105416,0.0001270854,0.0001063714,0.0002003845,0.0001657361,0.0002793687,0.0005739281,0.00005993475,0.00006112253],"category_scores_gemma":[0.00001968522,0.0001095343,0.00005201345,0.0002974133,0.00002608363,0.0004703724,0.00008932728,0.00009689984,0.00008780936],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008644366,"about_ca_system_score_gemma":0.00003143895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004941293,"about_ca_topic_score_gemma":0.000001771445,"domain_scores_codex":[0.9990122,0.00002122395,0.0002153129,0.000312349,0.0002224549,0.0002164764],"domain_scores_gemma":[0.9991319,0.00005123002,0.00008541597,0.0006565385,0.00002834094,0.00004661625],"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":[0.00002292264,0.0005811908,0.01280181,0.00003437097,0.00002891315,0.00004680387,0.000654337,0.03744249,0.03213253,0.4884066,0.001895688,0.4259523],"study_design_scores_gemma":[0.0003910869,0.0001423473,0.03107088,0.00005574481,0.000006805771,0.000006314982,0.00002389575,0.9532641,0.007551404,0.006944475,0.0002891526,0.000253822],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02878108,0.00001076137,0.9611779,0.003644519,0.0001989881,0.0001733674,3.131407e-7,0.0008597469,0.005153358],"genre_scores_gemma":[0.9515225,0.000002734816,0.04705164,0.000706127,0.00001767656,0.00000552983,0.000001719307,0.000004169778,0.0006879551],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9227414,"threshold_uncertainty_score":0.4466678,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03233434636012254,"score_gpt":0.2905214067512382,"score_spread":0.2581870603911156,"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."}}