{"id":"W2295468252","doi":"10.14778/2856318.2856325","title":"Combining quantitative and logical data cleaning","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":104,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University; McMaster University; University of Toronto","funders":"","keywords":"Computer science; Metric (unit); Inference; Functional dependency; Set (abstract data type); Distortion (music); Statistical inference; Data mining; Algorithm; Theoretical computer science; Dependency (UML); Quality (philosophy); Data quality; Artificial intelligence; Relational database; Mathematics","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":[0.005978244,0.00009779505,0.0002128958,0.00007374395,0.0001076004,0.0002372084,0.001859741,0.0000260165,0.00001893997],"category_scores_gemma":[0.004737836,0.00005502174,0.00003024039,0.0003319944,0.0001894309,0.0006538076,0.00362099,0.0001004695,0.00003071725],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002155951,"about_ca_system_score_gemma":0.0000188333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005733418,"about_ca_topic_score_gemma":0.000007735977,"domain_scores_codex":[0.9977972,0.00003188147,0.0004340434,0.0004197052,0.001146495,0.0001707099],"domain_scores_gemma":[0.9986349,0.0003081137,0.000333269,0.000377103,0.0002460384,0.0001006124],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001273223,0.0001800719,0.01047531,0.00003278647,0.00006513477,0.000001081392,0.005801457,0.00001746467,0.00139098,0.8257729,0.1355931,0.02054241],"study_design_scores_gemma":[0.002681357,0.0007681448,0.01429369,0.0002092316,0.0001273529,0.00002191315,0.1093953,0.00860213,0.005985488,0.5873224,0.2700839,0.0005090747],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8576558,0.000619131,0.002034704,0.01634783,0.0009504979,0.00106929,0.000142637,0.00009417782,0.1210859],"genre_scores_gemma":[0.9929789,0.00001873923,0.006020275,0.000415054,0.00002333814,0.000006020169,0.000003521576,0.000005000513,0.0005291247],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2384505,"threshold_uncertainty_score":0.5671975,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6149975953066957,"score_gpt":0.4683191180089634,"score_spread":0.1466784772977324,"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."}}