{"id":"W1626378195","doi":"10.1145/1938551.1938585","title":"Data cleaning and query answering with matching dependencies and matching functions","year":2011,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":69,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; International Business Machines Corporation","keywords":"Tuple; Matching (statistics); Computer science; Monotone polygon; Conjunctive query; Dependency (UML); Functional dependency; Semantics (computer science); Dependency theory (database theory); Query optimization; Upper and lower bounds; Theoretical computer science; Mathematics; Information retrieval; Discrete mathematics; Relational database; Artificial intelligence; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.002682222,0.0001040017,0.000147724,0.0001287497,0.0003290744,0.0005082656,0.0005340989,0.00002466115,0.0002489441],"category_scores_gemma":[0.0001559216,0.00006900512,0.000009542385,0.0001729763,0.00008762223,0.002071268,0.001372595,0.0001024103,0.00004250402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005568234,"about_ca_system_score_gemma":0.00001416532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001792816,"about_ca_topic_score_gemma":0.005569226,"domain_scores_codex":[0.9984892,0.00007155665,0.0002743815,0.0005203014,0.0004671768,0.0001774018],"domain_scores_gemma":[0.9986876,0.0003148634,0.00008582063,0.0007915698,0.00003369042,0.00008646237],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.0003021333,0.0002386019,0.0603885,0.0001728136,0.0003339726,0.0001713046,0.04355098,0.0001608553,0.000948936,0.4015342,0.0258708,0.4663269],"study_design_scores_gemma":[0.001412096,0.000342186,0.1997188,0.0002598643,0.000200762,0.0003177047,0.4543163,0.004884698,0.0002274531,0.2116903,0.1252211,0.001408605],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5379349,0.00007501179,0.4228636,0.0002719466,0.0001229343,0.0001147257,0.00006275924,0.00009173376,0.03846241],"genre_scores_gemma":[0.9638334,0.00002617346,0.03369413,0.0004425959,0.00002422445,0.000002629987,0.00001544147,0.000008539111,0.001952876],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4649183,"threshold_uncertainty_score":0.4901217,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3569999851508519,"score_gpt":0.3743921688869392,"score_spread":0.01739218373608725,"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."}}