{"id":"W2565034015","doi":"10.1109/iisa.2016.7785408","title":"Fuzzy joins in MapReduce: Edit and Jaccard distance","year":2016,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Jaccard index; Joins; Computer science; Edit distance; Similarity (geometry); Data mining; Fuzzy logic; Join (topology); Cluster analysis; Information retrieval; Artificial intelligence; Theoretical computer science; Mathematics; Programming language","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":[0.0000903074,0.00004927851,0.00005704807,0.00003077999,0.00003207767,0.00006207176,0.0003063501,0.00001765216,0.000008112083],"category_scores_gemma":[0.00001302694,0.0000312813,0.000008792856,0.0001426726,0.00003016132,0.0003330947,0.0001528606,0.00002668677,0.00005274736],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001274167,"about_ca_system_score_gemma":0.00001672978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002526999,"about_ca_topic_score_gemma":0.00002831029,"domain_scores_codex":[0.9994755,0.000007319831,0.00008788002,0.0002326561,0.00007219296,0.0001244989],"domain_scores_gemma":[0.9995481,0.00004309109,0.00001731075,0.0003304724,0.00001282671,0.00004824038],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[6.154365e-7,0.00003375471,0.00161427,0.000002701573,0.000002158352,0.000002926052,0.0001145682,2.61413e-7,0.001139741,0.3428749,0.02191223,0.6323019],"study_design_scores_gemma":[0.001701343,0.0001207183,0.2020797,0.0001722489,0.000005617611,0.00004327769,0.000106199,0.01337448,0.004862248,0.107153,0.6695339,0.0008472373],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01834914,0.0001034043,0.9502575,0.009714901,0.0001999032,0.0001030468,0.00002411731,0.0001244873,0.02112347],"genre_scores_gemma":[0.7941075,0.0001235986,0.2001882,0.0002957933,0.0001416197,0.0000518413,0.000002093857,0.000006406288,0.005082965],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7757583,"threshold_uncertainty_score":0.1275615,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01043677729507726,"score_gpt":0.2320618351602718,"score_spread":0.2216250578651945,"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."}}