{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00364493,0.00009488551,0.0002392333,0.0001403515,0.0000930063,0.0001332294,0.0006540548,0.0000275939,0.0001696173],"category_scores_gemma":[0.0004337756,0.00006664589,0.00009016752,0.000233471,0.00003676522,0.0005613246,0.0001734113,0.00004740156,0.00002056082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001951554,"about_ca_system_score_gemma":0.00001406123,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009008196,"about_ca_topic_score_gemma":0.00005204213,"domain_scores_codex":[0.9981295,0.00005893574,0.0006185274,0.0002846738,0.0006736291,0.0002346612],"domain_scores_gemma":[0.9989321,0.0003038037,0.0002274572,0.0003981332,0.00009094511,0.00004762316],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000209251,0.000184062,0.0004870936,0.0000339462,0.00002965592,0.000001822742,0.0008210294,0.0001750506,0.004972154,0.7796524,0.01686542,0.1965681],"study_design_scores_gemma":[0.004539859,0.0005273489,0.01274886,0.0001146911,0.00004189234,0.000005011044,0.01541176,0.006552519,0.04631647,0.8481599,0.06495101,0.0006306742],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3335114,0.00002627896,0.6426237,0.001446831,0.0001829284,0.0006227885,0.00009586925,0.00006720125,0.02142298],"genre_scores_gemma":[0.970821,0.000009201462,0.02672727,0.0007713967,0.00002198664,0.000008151767,0.000009775209,0.000003594358,0.001627664],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6373096,"threshold_uncertainty_score":0.2717741,"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."}}