{"id":"W2131815873","doi":"10.1145/1559845.1559891","title":"Incremental maintenance of length normalized indexes for approximate string matching","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Search engine indexing; Computer science; Security token; String (physics); Approximate string matching; Data mining; String searching algorithm; Matching (statistics); Key (lock); Similarity (geometry); False positive paradox; Feature (linguistics); Information retrieval; String metric; Limit (mathematics); Pattern matching; Theoretical computer science; Artificial intelligence; Mathematics","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":[0.005763809,0.0006910164,0.001704998,0.003611064,0.001132671,0.003253385,0.004581569,0.001263318,0.001411682],"category_scores_gemma":[0.04361888,0.0007104212,0.0007292722,0.005495593,0.00124935,0.007210013,0.002894692,0.001298089,0.001368055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001233866,"about_ca_system_score_gemma":0.002596659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002687501,"about_ca_topic_score_gemma":0.002753835,"domain_scores_codex":[0.9943413,0.001140976,0.0006340233,0.0009288311,0.002675883,0.0002789212],"domain_scores_gemma":[0.972955,0.008495847,0.002834472,0.0116673,0.003643195,0.0004041436],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005591951,0.0003448079,0.007065554,0.0003158211,0.0001320186,0.0002425159,0.0006664123,0.0852605,0.02036862,0.04143227,0.008825251,0.834787],"study_design_scores_gemma":[0.000139101,0.0003815948,0.002390082,0.00006073605,0.000178562,0.0008081667,0.000215658,0.8543391,0.04608418,0.07690357,0.01839546,0.0001037126],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01715643,0.0006453084,0.9764142,0.000176939,0.00006480667,0.0001492752,0.0002143074,0.004028546,0.001150202],"genre_scores_gemma":[0.2114089,0.0004743188,0.7844117,0.0001373988,0.0001703936,0.000261485,0.001183203,0.0003611469,0.001591566],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005763809,"threshold_uncertainty_score":0.03048235,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1302330347530281,"score_gpt":0.4050030461125494,"score_spread":0.2747700113595213,"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."}}