{"id":"W3129744650","doi":"10.14778/3436905.3436907","title":"Astrid","year":2020,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Substring; Computer science; Suffix; String (physics); Embedding; String searching algorithm; Suffix tree; Prefix; Theoretical computer science; Artificial intelligence; Algorithm; Pattern matching; Data structure; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001278874,0.002089757,0.001457095,0.001785918,0.001394594,0.004763247,0.004310462,0.002890059,0.3043495],"category_scores_gemma":[0.006468891,0.001083028,0.001461351,0.001965362,0.0006853819,0.006202341,0.005179907,0.002845559,0.3418496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001314766,"about_ca_system_score_gemma":0.002103468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003377701,"about_ca_topic_score_gemma":0.004702401,"domain_scores_codex":[0.9978883,0.0002440646,0.0001768555,0.0004951314,0.0009273037,0.0002683779],"domain_scores_gemma":[0.9974376,0.0003924532,0.0001362496,0.001095993,0.0007078768,0.0002298401],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003834506,0.00009439867,0.0008708062,0.0006248831,0.00005372445,0.0002250332,0.0001080731,0.002163166,0.002713276,0.01928807,0.8245985,0.1488767],"study_design_scores_gemma":[0.00007528558,0.00005365527,0.0003382589,0.00009183629,0.0000244818,0.0003175593,0.00007329498,0.007876948,0.003299845,0.01425279,0.9735537,0.00004218449],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.005981513,0.004031164,0.1374374,0.005060445,0.00357266,0.0008026523,0.07464096,0.2668212,0.5016518],"genre_scores_gemma":[0.06985603,0.004144786,0.1670884,0.007705679,0.0008750779,0.001095361,0.2620903,0.05130776,0.4358366],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3043495,"threshold_uncertainty_score":0,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2372725731202197,"score_gpt":0.3685803821593431,"score_spread":0.1313078090391233,"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."}}