{"id":"W2137775416","doi":"","title":"Improving data quality: consistency and accuracy","year":2007,"lang":"en","type":"article","venue":"Edinburgh Research Explorer (University of Edinburgh)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":312,"is_retracted":false,"has_abstract":true,"ca_institutions":"Bell (Canada)","funders":"Biotechnology and Biological Sciences Research Council; Engineering and Physical Sciences Research Council; Vlaamse regering; Fonds Wetenschappelijk Onderzoek","keywords":"Consistency (knowledge bases); Computer science; Data consistency; Data integrity; Consistency model; Sequential consistency; Set (abstract data type); Weak consistency; Heuristic; Data mining; Data quality; Quality (philosophy); Strong consistency; Database; Artificial intelligence; Mathematics; Programming language","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":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05447424,0.0002319622,0.0005974224,0.001473185,0.0009555885,0.0003199072,0.004640433,0.0001760347,0.00505869],"category_scores_gemma":[0.02253627,0.0002299472,0.0001225415,0.002132161,0.001734077,0.003431207,0.007978522,0.0006815409,0.00004847823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001003866,"about_ca_system_score_gemma":0.0002726957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002350342,"about_ca_topic_score_gemma":0.0006030811,"domain_scores_codex":[0.9915153,0.0004853786,0.0008395064,0.001484528,0.004661797,0.001013511],"domain_scores_gemma":[0.9816967,0.01174571,0.0005422751,0.00369432,0.001618496,0.0007024857],"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":[0.0003879935,0.0002372208,0.002631674,0.0000290332,0.00009950793,0.0001642234,0.007009476,0.000001952624,0.001838142,0.007447844,0.628711,0.3514419],"study_design_scores_gemma":[0.001625755,0.0002743789,0.005642102,0.00008165678,0.00004983075,0.000009355788,0.2338953,0.001465369,0.0002630349,0.04320715,0.7129754,0.0005106081],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6877916,0.001788661,0.2007928,0.02557966,0.00316596,0.00243725,0.0008788019,0.000332789,0.07723244],"genre_scores_gemma":[0.9793284,0.0007114592,0.006808088,0.0002164585,0.0005977855,0.000001260331,0.0001498663,0.00002147095,0.01216522],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3509313,"threshold_uncertainty_score":0.9958508,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5859534533824458,"score_gpt":0.5006272625830552,"score_spread":0.08532619079939052,"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."}}