{"id":"W2101821333","doi":"10.5430/air.v3n1p38","title":"A statistical approach for clustering in streaming data","year":2014,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Cluster analysis; Computer science; Data stream mining; Data stream clustering; Component (thermodynamics); Data mining; Context (archaeology); Data stream; Concept drift; Streaming data; Focus (optics); Unsupervised learning; Machine learning; CURE data clustering algorithm; Correlation clustering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.006205014,0.0001204353,0.0001816756,0.0003711002,0.0001742818,0.0004313738,0.003792272,0.00007789703,0.000008366314],"category_scores_gemma":[0.002870366,0.0001190507,0.00001855838,0.0007647977,0.0001969819,0.0006360391,0.002388308,0.0003662014,0.00004018822],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007455908,"about_ca_system_score_gemma":0.0001063389,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004919489,"about_ca_topic_score_gemma":0.0002593735,"domain_scores_codex":[0.9971462,0.0003226905,0.0003564113,0.0008866997,0.0005464677,0.0007414538],"domain_scores_gemma":[0.9960709,0.001766001,0.00003869455,0.001853596,0.000151609,0.0001192116],"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":[0.00001373158,0.0001257447,0.00008349563,0.00002784469,0.000002632405,0.000003545651,0.0002255569,0.0001139031,0.0003083016,0.2982174,0.0005818435,0.700296],"study_design_scores_gemma":[0.0000169635,0.0001382948,0.00006631983,0.00002775695,9.1756e-7,0.000003312154,0.0002175675,0.9247802,0.004708078,0.06888731,0.001028211,0.0001250807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001162448,0.00001210125,0.996157,0.0003130115,0.000058946,0.0004483795,0.00004603208,0.0001394089,0.001662655],"genre_scores_gemma":[0.4841844,0.000005832757,0.5155554,0.00001395333,0.00006847708,0.00007684041,0.00006898565,0.000009967319,0.0000161075],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9246663,"threshold_uncertainty_score":0.7047048,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4264192062234075,"score_gpt":0.4872538406245796,"score_spread":0.06083463440117209,"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."}}