{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004397595,0.000130477,0.0002713974,0.00008478633,0.0002555672,0.0001441013,0.004305646,0.00002819983,0.0001026041],"category_scores_gemma":[0.002536684,0.00007487221,0.00009972433,0.0003850528,0.0002239154,0.001027157,0.004286827,0.0001019861,0.0001080641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003656344,"about_ca_system_score_gemma":0.00002847438,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002921453,"about_ca_topic_score_gemma":0.00002114362,"domain_scores_codex":[0.9965878,0.00003038975,0.0007538665,0.0005427183,0.001848247,0.000237037],"domain_scores_gemma":[0.9979997,0.0002321048,0.0005117372,0.00102122,0.0001685729,0.00006665223],"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":[0.0001759446,0.0008405626,0.07481226,0.0002131513,0.0002167386,0.000003071587,0.006253954,0.00005269947,0.01485065,0.4062716,0.4563141,0.03999534],"study_design_scores_gemma":[0.001276041,0.00009761946,0.193402,0.0001276646,0.0000712369,0.00002542461,0.007961334,0.0005190978,0.03693907,0.1190325,0.6399669,0.000581099],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9511541,0.0001286295,0.0004584321,0.005143543,0.0004836817,0.0004645401,0.0003122495,0.00004861448,0.04180622],"genre_scores_gemma":[0.9942297,0.00008732842,0.0019098,0.0003389185,0.00007437031,0.00001265945,0.000009695446,0.000007553263,0.003329965],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2872391,"threshold_uncertainty_score":0.8001034,"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."}}