{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007931492,0.00003424883,0.0000664912,0.0001923875,0.0001515885,0.0001165755,0.0004289176,0.000006701148,0.00573918],"category_scores_gemma":[0.0002209759,0.00002748449,0.00002371071,0.0003993548,0.000008876453,0.0003103919,0.00060778,0.00009994431,0.0001975034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000044288,"about_ca_system_score_gemma":0.000009743066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001867228,"about_ca_topic_score_gemma":0.0002259124,"domain_scores_codex":[0.9984367,0.0003858898,0.0002338598,0.0001898535,0.0006541437,0.0000995278],"domain_scores_gemma":[0.9991779,0.0004695824,0.00005252251,0.000274056,0.000007915068,0.00001804515],"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":[0.0000191327,0.0000408028,0.0003642807,0.000001741247,0.000002611838,0.000005838767,0.0009275163,0.002369441,0.00009458994,0.8046829,0.005858328,0.1856328],"study_design_scores_gemma":[0.0001582037,0.00001606371,0.005438639,0.000001501301,0.000001387639,0.000001605492,0.04504518,0.0005038978,0.0001004116,0.7428617,0.205801,0.00007035668],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7761754,0.00002022167,0.107088,0.002087331,0.0007826053,0.0001764085,0.00001509031,0.000074224,0.1135807],"genre_scores_gemma":[0.9825419,0.000001874347,0.0003563159,0.0007817337,0.00001250815,0.00001204714,0.000003547816,0.000002124227,0.01628791],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2063665,"threshold_uncertainty_score":0.9951697,"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."}}