{"id":"W2789592939","doi":"10.5441/002/edbt.2018.87","title":"FastOFD: Contextual Data Cleaning with Ontology Functional Dependencies","year":2018,"lang":"en","type":"article","venue":"Movebank","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ontario Tech University; University of Waterloo; McMaster University","funders":"","keywords":"Computer science; Ontology; Functional dependency; Dependency theory (database theory); Information retrieval; Data mining; Relational database","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":["insufficient_payload"],"category_scores_codex":[0.002687359,0.0001198144,0.0001966298,0.0001282984,0.0002590996,0.0003027112,0.001566815,0.00005158872,0.003431075],"category_scores_gemma":[0.001386391,0.00008120228,0.00002640444,0.0002979303,0.0004204734,0.0009491522,0.001029774,0.0001106464,0.002460528],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000024229,"about_ca_system_score_gemma":0.00006711101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002219971,"about_ca_topic_score_gemma":0.005835426,"domain_scores_codex":[0.9973751,0.0001559343,0.0003719344,0.0006895432,0.001132716,0.0002747754],"domain_scores_gemma":[0.9973693,0.0005640788,0.0001548841,0.001579377,0.0002526273,0.000079691],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006205366,0.0001704231,0.02468429,0.000008419848,0.0001485354,0.00005914456,0.001176575,0.00005820047,0.0002020111,0.1838971,0.567093,0.2218818],"study_design_scores_gemma":[0.0008790408,0.0003629333,0.1090441,0.00001438515,0.0000252111,0.00003659034,0.003427903,0.001751803,0.0001795157,0.01218924,0.8718221,0.0002672765],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2443273,0.0001415735,0.5556008,0.003989126,0.002241549,0.0003862065,0.000512119,0.0002149583,0.1925863],"genre_scores_gemma":[0.9801137,0.00000222315,0.002426322,0.002869073,0.0003600864,0.000005428137,0.0001256147,0.000008833915,0.01408866],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7357864,"threshold_uncertainty_score":0.9983162,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4593973220632835,"score_gpt":0.4301787023006636,"score_spread":0.02921861976261991,"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."}}