{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006037337,0.0001015222,0.000211147,0.0001706591,0.0001149666,0.0001793656,0.000517865,0.00002122155,0.00009778157],"category_scores_gemma":[0.0005014068,0.00006827854,0.00003341303,0.0008933682,0.00004183703,0.0005126168,0.0002366327,0.00007826512,0.00005800087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004033648,"about_ca_system_score_gemma":0.00001641999,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002353768,"about_ca_topic_score_gemma":0.002457359,"domain_scores_codex":[0.9977478,0.00004604288,0.0004184452,0.0003888694,0.001098398,0.000300453],"domain_scores_gemma":[0.9985049,0.0006437191,0.000152793,0.0004752159,0.0001077385,0.0001156798],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003483506,0.0003271711,0.02210951,0.00008902882,0.00005447202,0.00005668218,0.001973997,0.00794528,0.003054458,0.3417899,0.006643932,0.6156073],"study_design_scores_gemma":[0.002714112,0.001281402,0.4921309,0.001056726,0.0001000031,0.00003502936,0.02087605,0.008962478,0.1071247,0.2239794,0.1393525,0.002386593],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2979231,0.000004506886,0.6935752,0.0001603955,0.0001243143,0.0001197944,0.000006634829,0.00003667321,0.008049347],"genre_scores_gemma":[0.9654484,6.900525e-7,0.03276875,0.0001327551,0.00004056298,0.000002453145,0.000001850078,0.0000060435,0.001598504],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6675252,"threshold_uncertainty_score":0.2784318,"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."}}