{"id":"W2048442462","doi":"10.1145/2133803.2184450","title":"StreamKM++","year":2012,"lang":"en","type":"article","venue":"ACM Journal of Experimental Algorithmics","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":295,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Algorithm; Computer science; Data stream; Tree (set theory); Sample (material); Sampling (signal processing); Streaming algorithm; Cluster analysis; Mathematics; Combinatorics; Upper and lower bounds; Artificial intelligence","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":[0.0003475197,0.0001373649,0.0001886724,0.0001337478,0.00005650009,0.00008637566,0.001767455,0.00005266305,0.00002395898],"category_scores_gemma":[0.0000956285,0.0001178886,0.00009713603,0.0001777498,0.00004531553,0.001825046,0.0007353874,0.0001750977,0.00002141087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001224859,"about_ca_system_score_gemma":0.00004923008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001004742,"about_ca_topic_score_gemma":7.775659e-8,"domain_scores_codex":[0.9987592,0.00004236103,0.0003575585,0.000111665,0.0003605142,0.0003686972],"domain_scores_gemma":[0.9986714,0.00007244753,0.0002875946,0.0006366975,0.00007916179,0.0002527418],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007460069,0.004403681,0.03103404,0.00001573638,0.0003947454,0.0003081261,0.01192599,0.000005435208,0.2136094,0.07450914,0.09041564,0.5733034],"study_design_scores_gemma":[0.0007544169,0.0008913094,0.002532327,0.00005782641,0.00001676105,0.00168089,0.0007087431,0.0006172594,0.9634644,0.002509906,0.02635401,0.0004120979],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5332254,0.01280798,0.4422491,0.000838172,0.004561166,0.0002444987,0.00002332772,0.000383401,0.005666959],"genre_scores_gemma":[0.4857931,0.0000498434,0.5137334,0.00011274,0.0002866804,0.000001486826,0.000001203057,0.000008073275,0.00001352718],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.749855,"threshold_uncertainty_score":0.4807359,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02788303691864616,"score_gpt":0.3083020289660293,"score_spread":0.2804189920473832,"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."}}