{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00519826,0.001059476,0.002058652,0.003017744,0.002456104,0.003357116,0.003442199,0.001474777,0.00140781],"category_scores_gemma":[0.01357988,0.0006858223,0.001397677,0.005083221,0.001182149,0.006357299,0.002830261,0.002105487,0.0007325145],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00118259,"about_ca_system_score_gemma":0.002167489,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004352004,"about_ca_topic_score_gemma":0.005628018,"domain_scores_codex":[0.9940566,0.001325224,0.0004303731,0.001010447,0.002886974,0.0002904614],"domain_scores_gemma":[0.9920353,0.003306186,0.0004383757,0.00198206,0.001873035,0.0003650087],"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":[0.001605907,0.001409961,0.007194051,0.0007618768,0.0005684814,0.0003597533,0.00179384,0.1572938,0.01412905,0.1504592,0.01919718,0.6452268],"study_design_scores_gemma":[0.0001703027,0.0006826127,0.002442365,0.00005259559,0.0001475897,0.0006245324,0.0007423674,0.7990578,0.0210739,0.1481041,0.02672522,0.0001765798],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0629938,0.001534192,0.9263244,0.0005895619,0.0005058309,0.0004522086,0.0004830936,0.001996059,0.00512093],"genre_scores_gemma":[0.3285016,0.0007440899,0.6653796,0.0002384082,0.0003514051,0.0002735741,0.0009602774,0.0003162019,0.003234965],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00519826,"threshold_uncertainty_score":0.02749133,"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."}}