{"id":"W3168081705","doi":"10.1109/rdaaps48126.2021.9452004","title":"An Overview of String Processing Applications to Data Analytics","year":2021,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Substring; Computer science; String (physics); Preprocessor; String searching algorithm; Pattern matching; Suffix array; Analytics; Trie; Suffix; Theoretical computer science; Data mining; Prefix; Data structure; Algorithm; Extension (predicate logic); Artificial intelligence; Programming language; 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":[0.0001113233,0.00004302395,0.00007784735,0.0000298515,0.000055218,0.0001086453,0.001187361,0.00001415902,0.00001985559],"category_scores_gemma":[0.00001024211,0.00003716566,0.000008726601,0.0005150426,0.000005773823,0.0006990144,0.001067139,0.00003131044,0.000006597481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005701218,"about_ca_system_score_gemma":0.00009895162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001747106,"about_ca_topic_score_gemma":0.00001319779,"domain_scores_codex":[0.9993303,0.00001310023,0.000131159,0.0002978191,0.0001448764,0.00008272667],"domain_scores_gemma":[0.9982393,0.00001486884,0.00003615482,0.001536166,0.0001034309,0.00007004499],"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":[4.111502e-7,0.0001198017,0.0001721281,0.00005548546,0.000004787236,0.000002877126,0.00007227334,0.0003178941,0.002632308,0.05039159,0.001176339,0.9450541],"study_design_scores_gemma":[0.00006349942,0.00001515961,0.001140658,0.00005422389,0.000006154919,0.000005091201,0.00005136953,0.9509973,0.005065354,0.001286358,0.0412106,0.000104225],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001891268,0.0006242048,0.9982985,0.0001930876,0.00001730052,0.00005312838,0.00001991527,0.00004140959,0.0005633602],"genre_scores_gemma":[0.08975121,0.00007179333,0.9096856,0.0002668462,0.00004391826,0.000004695311,0.00008631043,0.000003717316,0.00008591074],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9506794,"threshold_uncertainty_score":0.2206433,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2149976140574002,"score_gpt":0.4038099789852354,"score_spread":0.1888123649278352,"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."}}