{"id":"W1993831977","doi":"10.1145/1242524.1242529","title":"Estimating the selectivity of approximate string queries","year":2007,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Substring; String (physics); Estimator; Approximate string matching; Computer science; Inverse; String searching algorithm; String metric; Algorithm; String kernel; Data structure; Mathematics; Statistics; Pattern matching; Artificial intelligence","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":[0.005085166,0.0005060796,0.001518626,0.00309252,0.0006027263,0.002121457,0.001213995,0.00124379,0.0009385201],"category_scores_gemma":[0.04692527,0.0004425911,0.0004132787,0.003505429,0.0008848613,0.004911946,0.002109946,0.0009016392,0.0005464421],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001069317,"about_ca_system_score_gemma":0.001333863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002231394,"about_ca_topic_score_gemma":0.001714583,"domain_scores_codex":[0.9932328,0.001651903,0.0006822789,0.0007519881,0.003124716,0.0005562415],"domain_scores_gemma":[0.9667745,0.02367123,0.002313762,0.003843604,0.003056146,0.0003408174],"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":[0.003018658,0.0003022316,0.111644,0.0003467071,0.0001796053,0.0006601934,0.0007440451,0.2710517,0.03521158,0.0305765,0.006439193,0.5398257],"study_design_scores_gemma":[0.00003424431,0.0001083725,0.005065416,0.00001775943,0.00001864137,0.0004362765,0.0002497644,0.9638097,0.01507376,0.01399223,0.001168167,0.0000256569],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.421999,0.000864077,0.5711316,0.0005590445,0.00004554847,0.0001413995,0.001100776,0.001957788,0.00220072],"genre_scores_gemma":[0.8812813,0.0004835319,0.1151395,0.0001409624,0.0001121225,0.0001214611,0.001835047,0.0001308115,0.0007553216],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005085166,"threshold_uncertainty_score":0.02689326,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0257870433612683,"score_gpt":0.2745853299599472,"score_spread":0.2487982865986789,"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."}}