{"id":"W1967167578","doi":"10.14778/1453856.1453980","title":"Discovering data quality rules","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":268,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Data quality; Consistency (knowledge bases); Context (archaeology); Quality (philosophy); Data mining; Data integrity; Set (abstract data type); Data consistency; Process (computing); Database; Artificial intelligence; Programming language; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01511977,0.001813347,0.002101456,0.01194249,0.001823355,0.007347757,0.004192876,0.002377663,0.00227075],"category_scores_gemma":[0.10615,0.001572119,0.003998329,0.005548572,0.001834089,0.008104751,0.00468046,0.003941247,0.001131723],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002808427,"about_ca_system_score_gemma":0.006522246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008356454,"about_ca_topic_score_gemma":0.01122686,"domain_scores_codex":[0.9650422,0.004980867,0.005216945,0.005815096,0.01771588,0.001228974],"domain_scores_gemma":[0.8815446,0.07096115,0.009725274,0.01473743,0.02121326,0.001818291],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005732684,0.0009830564,0.1674478,0.003636991,0.001030492,0.003484358,0.002749587,0.05252321,0.01577806,0.06386509,0.03590264,0.6520255],"study_design_scores_gemma":[0.0001905392,0.0003615384,0.02417933,0.001836159,0.0007876817,0.002844309,0.002675211,0.6406669,0.0491715,0.1506765,0.1263214,0.0002889383],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09791879,0.002485348,0.8449972,0.005924887,0.0002697595,0.002182289,0.02652693,0.0113244,0.008370271],"genre_scores_gemma":[0.213557,0.0008566868,0.7521936,0.0009519063,0.0001054793,0.0007087578,0.02934587,0.0007992009,0.0014815],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01511977,"threshold_uncertainty_score":0.0799619,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4977714110126681,"score_gpt":0.451736219472416,"score_spread":0.04603519154025215,"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."}}