{"id":"W2107080109","doi":"10.14778/1454159.1454220","title":"A revival of integrity constraints for data cleaning","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"Bell (Canada)","funders":"Engineering and Physical Sciences Research Council","keywords":"Data integrity; Data quality; Computer science; Schema (genetic algorithms); Constraint (computer-aided design); Quality (philosophy); Risk analysis (engineering); Data science; Reliability engineering; Database; Information retrieval; Engineering; Operations management; Business; Mechanical engineering","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":[0.004840353,0.0001044202,0.0003107427,0.00008824202,0.0001344795,0.00004258924,0.002858227,0.0000336952,0.00007508502],"category_scores_gemma":[0.005566491,0.00006296614,0.0001173203,0.0003326968,0.0004278637,0.0004206564,0.001676512,0.0001100903,0.000009113499],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002364288,"about_ca_system_score_gemma":0.00004654112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005478925,"about_ca_topic_score_gemma":0.000004905837,"domain_scores_codex":[0.9976048,0.00001835082,0.0007493781,0.0003989694,0.001043222,0.0001852684],"domain_scores_gemma":[0.9979259,0.0003758355,0.000643418,0.0005806316,0.0004252218,0.00004893055],"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":[0.0002920827,0.0006098282,0.01364466,0.0004416227,0.0002077467,9.020353e-7,0.003684674,0.000005585712,0.0144174,0.3322641,0.5164315,0.118],"study_design_scores_gemma":[0.005120188,0.0007756673,0.01878162,0.0009966926,0.0003461252,0.00007815339,0.02519802,0.004605772,0.1807699,0.2314282,0.5310311,0.0008686247],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8500509,0.0004249006,0.01513927,0.01503947,0.00168231,0.005372691,0.001949904,0.0001165482,0.110224],"genre_scores_gemma":[0.9887461,0.00005381473,0.0101494,0.0002228591,0.00004457204,0.00001775867,0.000007155172,0.000006118999,0.0007522038],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1663525,"threshold_uncertainty_score":0.6664012,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5397355688626213,"score_gpt":0.4498791965858916,"score_spread":0.08985637227672966,"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."}}