{"id":"W4386843758","doi":"10.1109/dcc55655.2023.00023","title":"Computing matching statistics on Wheeler DFAs","year":2023,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"HORIZON EUROPE Health; National Human Genome Research Institute; Science and Engineering Research Council; National Institute of Allergy and Infectious Diseases; Gruppo Nazionale per il Calcolo Scientifico; National Institutes of Health; EGI; Israel Institute for Biological Research; Natural Sciences and Engineering Research Council of Canada; European Commission; Istituto Nazionale di Alta Matematica \"Francesco Severi\"; National Science Foundation","keywords":"Computer science; String searching algorithm; Suffix tree; Compressed suffix array; Deterministic finite automaton; Automaton; Pattern matching; Prefix; Tree (set theory); Matching (statistics); Subroutine; Algorithm; Theoretical computer science; Approximate string matching; String (physics); Suffix; Data structure; Mathematics; Combinatorics; Artificial intelligence; Programming language; Statistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001800361,0.00007874397,0.00007934125,0.00007472402,0.0001648197,0.0001717579,0.0004802364,0.00002334428,0.00003703159],"category_scores_gemma":[0.00001446943,0.00006178571,0.00001638858,0.0002760218,0.000009013731,0.0001972266,0.0005033972,0.00009508977,0.001079682],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001218091,"about_ca_system_score_gemma":0.00001746042,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006007759,"about_ca_topic_score_gemma":0.000003157099,"domain_scores_codex":[0.9991525,0.00002428194,0.0001240069,0.0002444884,0.0002384632,0.0002162477],"domain_scores_gemma":[0.9993489,0.0001710911,0.00003385244,0.0003611653,0.00002627532,0.00005875371],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001639148,0.00002884539,0.00009489358,0.0000104611,0.000006609382,0.00006331451,0.0005217449,0.00559714,0.000206502,0.5958317,0.1236497,0.2739875],"study_design_scores_gemma":[0.0001189868,0.00003475999,0.006105852,0.00002475266,7.820564e-7,0.00000339589,0.00003246344,0.975172,0.0001433711,0.01050734,0.007732473,0.0001237978],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005805857,0.000003980652,0.988972,0.0002796498,0.0004518663,0.00004438993,0.000009201363,0.0005336123,0.003899425],"genre_scores_gemma":[0.230536,0.00001082852,0.765904,0.0009106712,0.0001732185,0.000001956203,0.00004159838,0.00001435936,0.002407405],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9695749,"threshold_uncertainty_score":0.9996981,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02391902105475247,"score_gpt":0.2826896403153684,"score_spread":0.258770619260616,"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."}}