{"id":"W1886218757","doi":"10.1109/icdm.2002.1183904","title":"Phrase-based document similarity based on an index graph model","year":2003,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Document clustering; Cluster analysis; Phrase; Vector space model; Information retrieval; Graph; Similarity (geometry); Matching (statistics); Set (abstract data type); Artificial intelligence; Data mining; 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":[],"consensus_categories":[],"category_scores_codex":[0.0005378005,0.0001544104,0.0001522231,0.0002115309,0.0001373411,0.0002194085,0.0006669237,0.0000564513,0.0000974411],"category_scores_gemma":[0.00003817309,0.0001279786,0.00009917311,0.0005192706,0.00002774767,0.0003763963,0.00003444301,0.0001205855,0.00003016027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003101855,"about_ca_system_score_gemma":0.0001568981,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007933179,"about_ca_topic_score_gemma":0.00004243707,"domain_scores_codex":[0.9985147,0.0001339715,0.0001739489,0.0005124386,0.0003977117,0.0002672716],"domain_scores_gemma":[0.998526,0.00004994873,0.00004931372,0.001150018,0.00004715626,0.0001775995],"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":[0.00001392617,0.0006718919,0.004211195,0.000009728397,0.00002482146,0.00001956037,0.00007318374,0.9162505,0.000191354,0.06862238,0.003584889,0.006326613],"study_design_scores_gemma":[0.0004183367,0.00008131817,0.0001880376,0.000006694433,0.000009340277,2.673653e-7,0.000008631894,0.9930756,0.002131409,0.003432481,0.0004618049,0.0001860701],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01164468,0.000003757931,0.9805255,0.0006824785,0.00004519683,0.0000523239,0.000006672587,0.0001875319,0.006851853],"genre_scores_gemma":[0.8798538,5.264528e-7,0.1161235,0.00378392,0.000008024847,0.000007676715,0.00001640824,0.000006015527,0.0002000788],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8682092,"threshold_uncertainty_score":0.5218815,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02070779077958386,"score_gpt":0.2583232720134422,"score_spread":0.2376154812338583,"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."}}