{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002313925,0.0009760848,0.001947707,0.005637283,0.0009842073,0.002523417,0.001476879,0.001202985,0.0006945477],"category_scores_gemma":[0.009008387,0.0004417996,0.001613922,0.007031005,0.0008122841,0.004162468,0.001371011,0.001129017,0.0008725738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001553452,"about_ca_system_score_gemma":0.001702065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004300952,"about_ca_topic_score_gemma":0.003438287,"domain_scores_codex":[0.9974129,0.0007028649,0.0002439937,0.0005737708,0.0009345716,0.0001319243],"domain_scores_gemma":[0.9960195,0.001450781,0.000658106,0.000711355,0.001057491,0.0001027295],"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":[0.0005425037,0.0003664848,0.007914921,0.0005156265,0.0006400158,0.0001612394,0.0005232856,0.2497593,0.02300919,0.03631673,0.004958329,0.6752924],"study_design_scores_gemma":[0.00001814207,0.00007187764,0.001895125,0.00002091182,0.00006477584,0.0001546476,0.0000588667,0.9778243,0.005861224,0.01257703,0.001400978,0.00005202414],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03437319,0.0005906987,0.9630045,0.0000869491,0.00003430981,0.0000782023,0.0001493433,0.0009750405,0.000707757],"genre_scores_gemma":[0.4084407,0.0006916514,0.5879416,0.00005049951,0.00009252237,0.0001804276,0.001054129,0.000210329,0.001338174],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005637283,"threshold_uncertainty_score":0.01223737,"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."}}