{"id":"W2112840274","doi":"10.14778/1920841.1920870","title":"Sampling the repairs of functional dependency violations under hard constraints","year":2010,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":127,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Dependency (UML); Class (philosophy); Functional dependency; Context (archaeology); Sampling (signal processing); Relation (database); Data integrity; Variety (cybernetics); Space (punctuation); Data mining; Metric (unit); Theoretical computer science; Relational database; Database; Artificial intelligence","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":[0.003644981,0.0001058837,0.0001723385,0.0001013614,0.0002576671,0.0001093144,0.001103403,0.00004486698,0.0007046714],"category_scores_gemma":[0.001882149,0.00005459006,0.0001697858,0.0004129858,0.0004269395,0.0002808494,0.0005194222,0.0002137205,0.00003287273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002048068,"about_ca_system_score_gemma":0.00005185003,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004213702,"about_ca_topic_score_gemma":0.000041651,"domain_scores_codex":[0.9975303,0.00001934611,0.0006479094,0.000293113,0.001337835,0.0001714298],"domain_scores_gemma":[0.9980634,0.000503447,0.0005448339,0.0003689323,0.0004717317,0.00004766303],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000406563,0.0001996949,0.01277916,0.00002871053,0.0001087568,7.878107e-8,0.000861121,0.0001811694,0.08822781,0.8685724,0.01487159,0.01412882],"study_design_scores_gemma":[0.000885231,0.00008789302,0.2274871,0.0000849232,0.0001446285,0.00002148475,0.01379489,0.0007074735,0.03541622,0.6822823,0.03880276,0.0002850734],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9262955,0.00003980305,0.008185695,0.0141309,0.002090576,0.001087377,0.0001220881,0.00005823748,0.04798984],"genre_scores_gemma":[0.9962366,0.000007060673,0.00241368,0.0002966667,0.00006387834,0.00002466461,0.000001866997,0.000005380852,0.000950246],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.214708,"threshold_uncertainty_score":0.7715657,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1812498346188758,"score_gpt":0.3696657815601582,"score_spread":0.1884159469412824,"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."}}