{"id":"W4366959045","doi":"10.1109/wi-iat55865.2022.00014","title":"SMAT: String Matching in Action Theory","year":2022,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"","keywords":"String metric; String searching algorithm; Computer science; Heuristics; Edit distance; Approximate string matching; Commentz-Walter algorithm; Matching (statistics); Levenshtein distance; Formalism (music); String (physics); Pattern matching; Artificial intelligence; Theoretical computer science; Mathematics; Theoretical physics; Physics","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":[0.003576146,0.001034787,0.001104864,0.002884514,0.001561973,0.003587903,0.003172004,0.002347432,0.01269481],"category_scores_gemma":[0.007979453,0.0007581114,0.003449671,0.002863,0.004810775,0.006474875,0.003570611,0.003365047,0.003705856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002198512,"about_ca_system_score_gemma":0.002308445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003411318,"about_ca_topic_score_gemma":0.002271083,"domain_scores_codex":[0.9964714,0.00126855,0.0003813477,0.0007465403,0.0009009509,0.0002312746],"domain_scores_gemma":[0.9981085,0.001043126,0.000172164,0.0003300539,0.0002361834,0.0001099854],"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":[0.00005448078,0.00003333623,0.0002063715,0.0001478705,0.00002756437,0.0001052871,0.0002632069,0.01671219,0.0009095653,0.9281453,0.003413511,0.04998121],"study_design_scores_gemma":[0.00002063434,0.00003797307,0.00007901425,0.00004890485,0.00001708855,0.00007676201,0.00005275811,0.1177812,0.001306506,0.8590727,0.02148541,0.00002094638],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00105641,0.0001244744,0.9937612,0.0001962349,0.00007484802,0.00008156218,0.0001750308,0.00124806,0.003282126],"genre_scores_gemma":[0.08168665,0.0004078607,0.9104068,0.0003653798,0.0002208044,0.0006647462,0.0008670376,0.0006114382,0.004769328],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01269481,"threshold_uncertainty_score":0.04246837,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3388031006794953,"score_gpt":0.4670978388625993,"score_spread":0.128294738183104,"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."}}