{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006641858,0.0007913992,0.00146591,0.001428963,0.0007763588,0.001059771,0.00187476,0.00159415,0.001044564],"category_scores_gemma":[0.04814147,0.0006231864,0.001155796,0.001318159,0.001356201,0.002132396,0.001753863,0.001797797,0.0002708242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000941277,"about_ca_system_score_gemma":0.001745098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002166295,"about_ca_topic_score_gemma":0.003335025,"domain_scores_codex":[0.9940351,0.002546913,0.0005231496,0.001137419,0.001386441,0.0003710587],"domain_scores_gemma":[0.9459171,0.04035443,0.002856625,0.007591051,0.00261215,0.0006686944],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001354502,0.0005490964,0.02676857,0.000587062,0.0002555318,0.0006628524,0.001289465,0.6412677,0.0165975,0.01659114,0.006223891,0.2878526],"study_design_scores_gemma":[0.00008066854,0.0002045106,0.001781795,0.0000381374,0.00006413247,0.0003125748,0.0003469138,0.9594907,0.01157619,0.02432048,0.001757698,0.00002626009],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3402188,0.0006179192,0.6543396,0.0009551736,0.00005330814,0.0003085658,0.0006021249,0.001720676,0.001183741],"genre_scores_gemma":[0.7143211,0.000178144,0.2826576,0.000211905,0.00004555859,0.000273417,0.001250731,0.0002609746,0.000800503],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006641858,"threshold_uncertainty_score":0.03512597,"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."}}