{"id":"W1970107047","doi":"10.1109/icmlc.2010.5580499","title":"Incremental clustering algorithm based on phrase-semantic similarity histogram","year":2010,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Computer science; Fuzzy clustering; Correlation clustering; CURE data clustering algorithm; Canopy clustering algorithm; Document clustering; Data stream clustering; Data mining; Artificial intelligence; Clustering high-dimensional data; Brown clustering; Single-linkage clustering; Pattern recognition (psychology); Information retrieval","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":[0.0003556178,0.0001273205,0.0001365644,0.0001423569,0.0001515187,0.000194329,0.0007450153,0.00005393796,0.0001705462],"category_scores_gemma":[0.00003707172,0.0001103982,0.00008403988,0.0002847784,0.00003644817,0.0002375197,0.0002252092,0.0002331248,0.000122021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002383068,"about_ca_system_score_gemma":0.00003572541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003376441,"about_ca_topic_score_gemma":0.000207645,"domain_scores_codex":[0.9988868,0.00003268452,0.0001608012,0.0003882449,0.0002949719,0.0002365588],"domain_scores_gemma":[0.9989889,0.00005239302,0.00004697782,0.0007729217,0.00002765935,0.0001111111],"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":[0.000007761668,0.0006660915,0.003711253,0.00002519612,0.00005435276,0.0000987365,0.0001860509,0.0005894944,0.01484624,0.002178901,0.009405531,0.9682304],"study_design_scores_gemma":[0.0002237548,0.00005106705,0.0009105459,0.000007696409,0.000009822286,0.000003823872,0.00001061189,0.9932473,0.001810184,0.0000458949,0.003519329,0.0001599369],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0137268,0.000002507499,0.979776,0.0008115463,0.0003875718,0.00005235364,0.000007483779,0.0002750748,0.004960639],"genre_scores_gemma":[0.696731,4.192799e-7,0.3020943,0.0009044078,0.00006260157,0.000003771048,0.00001153021,0.000005561609,0.0001864443],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9926578,"threshold_uncertainty_score":0.4501908,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01338385580906149,"score_gpt":0.243526709109979,"score_spread":0.2301428533009175,"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."}}