{"id":"W2207847180","doi":"10.14778/2824032.2824049","title":"Fuzzy joins in MapReduce","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Joins; Skyline; Computer science; Point (geometry); Hamming distance; Fuzzy logic; Binary number; Algorithm; Data mining; Theoretical computer science; Artificial intelligence; Mathematics; Programming language; Arithmetic","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003682473,0.001106346,0.001233245,0.001178205,0.002663789,0.002551766,0.003208284,0.001238626,0.005290372],"category_scores_gemma":[0.00666024,0.0006251184,0.001096487,0.002658746,0.001034034,0.005090884,0.002753319,0.001856405,0.001818899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001411006,"about_ca_system_score_gemma":0.00234579,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00771948,"about_ca_topic_score_gemma":0.007308594,"domain_scores_codex":[0.994206,0.001015159,0.0003348147,0.0009758055,0.002836796,0.0006315451],"domain_scores_gemma":[0.9954569,0.001666658,0.0001614307,0.001480365,0.0008393305,0.0003953603],"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":[0.007912346,0.004774502,0.01152817,0.002698198,0.000791632,0.0008027307,0.002060876,0.2320347,0.04475654,0.06991165,0.09677851,0.5259502],"study_design_scores_gemma":[0.001189408,0.001951098,0.004962292,0.0001123734,0.0002592803,0.0009159695,0.002116526,0.7185494,0.07701304,0.1252849,0.06747071,0.0001749721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5174333,0.003930237,0.3509867,0.002831233,0.001585283,0.001607601,0.005729274,0.03777688,0.07811945],"genre_scores_gemma":[0.6643422,0.0007647894,0.3223282,0.0006564548,0.0002267289,0.000395999,0.005470452,0.0006303902,0.005184684],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.00771948,"threshold_uncertainty_score":0.01947504,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03116395072858845,"score_gpt":0.245206021545165,"score_spread":0.2140420708165766,"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."}}