{"id":"W2149433841","doi":"10.1109/wi.2003.1241276","title":"Incremental document clustering using cluster similarity histograms","year":2004,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Computer science; Document clustering; Fuzzy clustering; Data mining; Information retrieval; Brown clustering; Conceptual clustering; Correlation clustering; Histogram; Consensus clustering; Similarity measure; Similarity (geometry); CURE data clustering algorithm; Artificial intelligence; Image (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":[0.0003913557,0.0002125807,0.0001872086,0.0001507885,0.0002743494,0.0002977788,0.001054225,0.00007106879,0.00003974793],"category_scores_gemma":[0.00002745627,0.0002031922,0.00008237133,0.0004114201,0.00008024929,0.001104562,0.001845628,0.0002591856,0.00006598567],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001053944,"about_ca_system_score_gemma":0.0001062911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006532472,"about_ca_topic_score_gemma":0.0001221871,"domain_scores_codex":[0.9977665,0.00005470887,0.0003088084,0.000574402,0.0006488825,0.0006467156],"domain_scores_gemma":[0.9988803,0.00003631282,0.00006540506,0.000726264,0.00007937921,0.0002123482],"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":[0.00007540415,0.000542098,0.0003746765,0.0001654759,0.000129139,0.0003559832,0.002703671,0.7200405,0.02544394,0.01877986,0.0001719235,0.2312173],"study_design_scores_gemma":[0.003025505,0.0002680305,0.0003638166,0.00009236231,0.000008931454,0.0003061626,0.0001421328,0.9645935,0.01484256,0.01257053,0.002951825,0.0008346202],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02756285,0.00004187772,0.9689276,0.0008962742,0.0003679415,0.0002831023,7.500897e-7,0.0003417825,0.001577808],"genre_scores_gemma":[0.4151987,0.000005187383,0.584012,0.0005027912,0.00006574319,0.00001190634,0.000001050144,0.00001629423,0.0001862863],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3876359,"threshold_uncertainty_score":0.8285937,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03597026134903813,"score_gpt":0.3216917714434714,"score_spread":0.2857215100944333,"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."}}