{"id":"W1564399566","doi":"","title":"Accuracy of Approximate String Joins Using Grams","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Substring; Joins; Similarity (geometry); Computer science; Data mining; String (physics); String metric; Matching (statistics); Join (topology); String searching algorithm; Algorithm; Pattern matching; Pattern recognition (psychology); Artificial intelligence; Mathematics; Statistics; Data structure","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":[0.006383631,0.00006389373,0.0001545827,0.0001824742,0.00006525265,0.0001159797,0.0005327268,0.00002545983,0.0003661371],"category_scores_gemma":[0.001349906,0.00004476779,0.00005885524,0.0005374992,0.00005307426,0.0004657565,0.0003298503,0.00004598684,0.00007282237],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001496688,"about_ca_system_score_gemma":0.00001646205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002654316,"about_ca_topic_score_gemma":0.0001208122,"domain_scores_codex":[0.9981083,0.000045566,0.0005904283,0.0002253667,0.0008292521,0.0002010606],"domain_scores_gemma":[0.998408,0.0006764733,0.0002279065,0.0005339744,0.00009344419,0.00006023102],"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":[0.00003489123,0.0001744643,0.004276438,0.00002856658,0.00002728066,0.00001185241,0.0006629005,0.0002842522,0.005045198,0.3948303,0.004244573,0.5903793],"study_design_scores_gemma":[0.002207171,0.0002160235,0.04262983,0.0001284857,0.00008401508,0.00001914637,0.03972926,0.03676629,0.143361,0.3241499,0.409598,0.001110901],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3369992,0.00002054095,0.6332073,0.000115339,0.0001790464,0.0001194979,0.000007742892,0.00002842949,0.02932283],"genre_scores_gemma":[0.9769241,0.000005260465,0.02176538,0.0002088518,0.00002698378,3.822302e-7,0.000002580307,0.000003536816,0.001062968],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6399248,"threshold_uncertainty_score":0.4008944,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3939898281848053,"score_gpt":0.4885599141472641,"score_spread":0.0945700859624588,"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."}}