{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001108473,0.0001271105,0.0001619928,0.0001010573,0.0003724879,0.00009327244,0.0009795231,0.00003743953,0.000004320801],"category_scores_gemma":[0.00005615739,0.00008790805,0.00004792118,0.0004505019,0.00005093674,0.0006701408,0.00005683245,0.0002077368,0.000007032083],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003277867,"about_ca_system_score_gemma":0.00004186483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006743145,"about_ca_topic_score_gemma":0.00004156485,"domain_scores_codex":[0.9987236,0.0000849596,0.0003156314,0.0003000883,0.0003362077,0.000239461],"domain_scores_gemma":[0.9977694,0.0004218685,0.0001455933,0.001538795,0.00006458361,0.00005981061],"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":[0.0001611612,0.001163655,0.000674953,0.001105537,0.0003122696,0.00007373625,0.003617494,0.1168229,0.03319674,0.05399875,0.0009992147,0.7878736],"study_design_scores_gemma":[0.0004520912,0.000124118,0.0005994808,0.0004399066,0.00002627779,0.0001076512,0.0003918915,0.9549856,0.03957935,0.0003621578,0.002603059,0.0003284636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00885549,0.00009512026,0.9896277,0.00006814308,0.0007449384,0.0002371702,0.0001272055,0.0001291744,0.0001150633],"genre_scores_gemma":[0.8386069,0.000005119525,0.1612456,0.00001450302,0.00005704597,0.00001831186,0.0000121939,0.000007923099,0.00003234365],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8381626,"threshold_uncertainty_score":0.3584787,"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."}}