{"id":"W2923023146","doi":"10.1109/tbdata.2019.2907624","title":"Hierarchical Density-Based Clustering Using MapReduce","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Big Data","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Fundação de Amparo à Pesquisa do Estado de Minas Gerais; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Natural Sciences and Engineering Research Council of Canada; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Computer science; Cluster analysis; Scalability; Automatic summarization; Correlation clustering; Hierarchical clustering; CURE data clustering algorithm; Data mining; Canopy clustering algorithm; Constrained clustering; Artificial intelligence; Database","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003057414,0.0001854831,0.0001892616,0.0002699253,0.0002263518,0.0001845885,0.002320303,0.00008562766,0.00002621226],"category_scores_gemma":[0.00000979668,0.0001913558,0.00005417021,0.0005586991,0.00006620746,0.0006934666,0.00007049834,0.0005235679,0.0002543227],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001275846,"about_ca_system_score_gemma":0.0001987996,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006764437,"about_ca_topic_score_gemma":0.00003557301,"domain_scores_codex":[0.9978163,0.0001097671,0.0002207579,0.0008498663,0.0005388349,0.0004644343],"domain_scores_gemma":[0.9966199,0.0001962321,0.00004447554,0.002905955,0.00006183727,0.0001716381],"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":[0.00008229368,0.0002587442,0.0000183786,0.00008357862,0.00004529212,0.00006315371,0.0001142233,0.4344054,0.03075355,0.00003754806,0.00005579352,0.5340821],"study_design_scores_gemma":[0.0004784585,0.00007733131,0.00004647496,0.00005991929,0.000006060511,0.00004491842,0.000006677362,0.978183,0.01996322,0.00005898517,0.0008576267,0.0002173573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02074375,0.000009000662,0.9766394,0.0003776186,0.001608636,0.0002408184,0.00008248052,0.000219642,0.00007860237],"genre_scores_gemma":[0.7608311,0.000005505023,0.2385696,0.0002157802,0.00008346354,0.000006966994,0.0000116424,0.00002582578,0.0002500784],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7400874,"threshold_uncertainty_score":0.7803263,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1308743166587772,"score_gpt":0.3353534078399405,"score_spread":0.2044790911811633,"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."}}