{"id":"W2137763598","doi":"10.1109/tkde.2004.58","title":"Efficient phrase-based document indexing for Web document clustering","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":320,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Document clustering; Computer science; Cluster analysis; Vector space model; Search engine indexing; Phrase; Information retrieval; Document classification; Data mining; tf–idf; Artificial intelligence; Term (time)","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":[0.0003419823,0.0002049949,0.0001926514,0.0002855363,0.0002133799,0.0002177284,0.0006802019,0.00005285157,0.000004958067],"category_scores_gemma":[0.000008043313,0.0002021405,0.0000673313,0.0003431034,0.00001614486,0.0003144251,0.00002518323,0.0001446296,0.00001762712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001009411,"about_ca_system_score_gemma":0.00008974737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000186786,"about_ca_topic_score_gemma":0.00003339825,"domain_scores_codex":[0.9986981,0.00001259748,0.0002472124,0.0005792846,0.0001507878,0.0003120013],"domain_scores_gemma":[0.9987521,0.0001044905,0.00003679768,0.000934187,0.00003374653,0.0001387132],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000821009,0.000105566,0.000001027519,0.00008869779,0.00005468107,0.000003846004,0.0002296668,0.9700858,0.001920419,0.0003200825,0.00003901521,0.027143],"study_design_scores_gemma":[0.001064808,0.00007637138,0.000009209919,0.0001740748,0.00005016522,0.00000569945,0.00001882931,0.9885849,0.006719325,0.00001931992,0.003021014,0.0002562322],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007419664,0.0001950593,0.9911999,0.0001820255,0.0004795745,0.0001662769,0.0001075544,0.0002164863,0.00003342925],"genre_scores_gemma":[0.9234667,0.00001709425,0.07628253,0.00003994777,0.00005907203,0.00005234398,0.00003098117,0.00001778425,0.00003357515],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.916047,"threshold_uncertainty_score":0.8243051,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02028388213544066,"score_gpt":0.2679597706680517,"score_spread":0.247675888532611,"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."}}