{"id":"W1578664299","doi":"","title":"Extending q-grams to estimate selectivity of string matching with low edit distance","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":50,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Edit distance; Approximate string matching; String searching algorithm; String metric; Computer science; String (physics); Algorithm; Boyer–Moore string search algorithm; Matching (statistics); Similarity (geometry); Theoretical computer science; Data mining; Pattern matching; Mathematics; Artificial intelligence; Statistics; Image (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":[0.003826639,0.0005366561,0.001238076,0.003146745,0.0004569109,0.001133297,0.001346476,0.0008381152,0.0008064439],"category_scores_gemma":[0.02368403,0.0003439219,0.0005091266,0.002562485,0.0007846723,0.003117189,0.001356934,0.0007552242,0.0003823424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007511174,"about_ca_system_score_gemma":0.001032268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00246571,"about_ca_topic_score_gemma":0.00230086,"domain_scores_codex":[0.99708,0.0008744101,0.0002634919,0.0004368364,0.001160217,0.0001849551],"domain_scores_gemma":[0.9838155,0.01154747,0.001413785,0.001432678,0.001565495,0.0002250911],"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":[0.0007142143,0.0002243138,0.04337535,0.0003814039,0.0001408811,0.0003753524,0.0004235797,0.1935787,0.04118019,0.04158651,0.002057892,0.6759616],"study_design_scores_gemma":[0.00002216885,0.0001209736,0.002715251,0.00001267125,0.00001792931,0.0002759857,0.00007185847,0.9555904,0.01488885,0.02525189,0.001006497,0.00002563458],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0558308,0.0001633527,0.9427103,0.0000686932,0.00000942077,0.00005226845,0.0001221795,0.0006127775,0.0004301149],"genre_scores_gemma":[0.4743497,0.0001620854,0.524352,0.00007058591,0.00004341544,0.00009686477,0.0003920192,0.0000724468,0.0004608986],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003826639,"threshold_uncertainty_score":0.02023739,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.062628898205617,"score_gpt":0.4288560674720442,"score_spread":0.3662271692664272,"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."}}