{"id":"W151938044","doi":"10.1137/1.9781611972757.5","title":"Summarizing and Mining Skewed Data Streams","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":138,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Crohn's and Colitis Foundation of Canada","keywords":"Skew; Skewness; Data stream mining; Computer science; Data mining; Data stream; Space (punctuation); Zipf's law; Point (geometry); Algorithm; Mathematics; Statistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002026451,0.00005756654,0.0000540783,0.00004031153,0.00006110873,0.000330291,0.0010925,0.00001147723,0.00002198918],"category_scores_gemma":[0.00001266172,0.0000488531,0.000005466548,0.0001062785,0.00001338355,0.001967144,0.001929257,0.00002837288,0.00003660934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004024475,"about_ca_system_score_gemma":0.000006114422,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002468114,"about_ca_topic_score_gemma":0.00004325037,"domain_scores_codex":[0.9993622,0.000008854534,0.00008190328,0.0003043716,0.0001027786,0.0001399483],"domain_scores_gemma":[0.9991279,0.0000291149,0.00001982877,0.0007748941,0.000006672959,0.00004156562],"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":[2.220974e-7,0.00001033342,0.0004825184,0.000002221369,0.000005895839,0.000003096078,0.00005524644,0.000002017159,0.00001438571,0.01633627,0.01541376,0.967674],"study_design_scores_gemma":[0.0002047455,0.00001271237,0.001026583,0.000007382549,0.000004415238,0.000002643644,0.00005997378,0.7330445,0.00008643216,0.0002002541,0.2652194,0.0001309703],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01252767,0.0002389159,0.9074159,0.00546939,0.0002432125,0.0001230983,0.00001470605,0.0003971092,0.07356995],"genre_scores_gemma":[0.1009138,0.00005545361,0.892353,0.0008377933,0.000178527,0.000001478033,0.00007296902,0.00000543188,0.005581575],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9675431,"threshold_uncertainty_score":0.3185004,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04579868955532916,"score_gpt":0.2686245177712225,"score_spread":0.2228258282158933,"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."}}