{"id":"W2039548475","doi":"10.1145/2588555.2610520","title":"Descriptive and prescriptive data cleaning","year":2014,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Tuple; Scalability; Data mining; Transformation (genetics); Decoupling (probability); Quality (philosophy); Benchmark (surveying); Data quality; Data source; Database; 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":[0.00506429,0.00007238337,0.0001342152,0.00008169478,0.0001131609,0.0004321623,0.001200096,0.00002229614,0.0003700422],"category_scores_gemma":[0.003581277,0.00004908242,0.0000128491,0.0001750214,0.00009991907,0.001130864,0.001939614,0.00005828188,0.0004278288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006613563,"about_ca_system_score_gemma":0.000007984123,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001785978,"about_ca_topic_score_gemma":0.0002546033,"domain_scores_codex":[0.9982441,0.0002332444,0.000260213,0.0005464773,0.000568294,0.0001476494],"domain_scores_gemma":[0.9978809,0.0005983422,0.00007419627,0.001296703,0.00006885793,0.00008096251],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001708788,0.00002714836,0.001167456,0.000002875176,0.00001659506,0.000001379894,0.00113086,0.000003414112,0.00005701181,0.3397593,0.3353731,0.3224438],"study_design_scores_gemma":[0.0002258963,0.00005701527,0.01196234,0.000006252119,0.00001141148,0.0000015041,0.00785686,0.01489346,0.00006660177,0.07760011,0.8871933,0.0001253045],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02575011,0.00006265545,0.5966172,0.002901387,0.0004774856,0.0002523853,0.00009862877,0.0001040996,0.3737361],"genre_scores_gemma":[0.970157,0.00001217594,0.01331261,0.001975416,0.00007141922,0.000002699193,0.00002825822,0.000005519168,0.01443489],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9444069,"threshold_uncertainty_score":0.5499016,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4878263125069607,"score_gpt":0.4445102663131563,"score_spread":0.04331604619380447,"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."}}