{"id":"W2544486974","doi":"10.14778/2994509.2994518","title":"Detecting data errors","year":2016,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":237,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"University of California Berkeley","keywords":"Computer science; Raw data; Outlier; Data mining; Set (abstract data type); Variety (cybernetics); Data quality; Ground truth; Anomaly detection; Quality (philosophy); Big data; Data science; Machine learning; Artificial intelligence; 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":[0.00496573,0.0001076389,0.0001800164,0.0001027757,0.0001386065,0.0001218161,0.004188958,0.00002737488,0.0001856214],"category_scores_gemma":[0.00501184,0.00004614924,0.00007127508,0.0004263165,0.0001240579,0.0007866435,0.003694214,0.00005910585,0.0001515044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003851822,"about_ca_system_score_gemma":0.00001678737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004514522,"about_ca_topic_score_gemma":0.00001874168,"domain_scores_codex":[0.9973492,0.00001971414,0.0005474916,0.0004984864,0.001347826,0.000237257],"domain_scores_gemma":[0.9980723,0.0003440704,0.000466794,0.0008638618,0.0001922365,0.00006070064],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007913954,0.0001948257,0.01391979,0.00005613091,0.0001070928,6.834094e-7,0.0009899496,0.000002379312,0.0868101,0.07285151,0.2312869,0.5937015],"study_design_scores_gemma":[0.001125774,0.0001114514,0.009615254,0.0002392657,0.0000709224,0.00000861578,0.004676851,0.0001844982,0.1827602,0.1383543,0.6625121,0.0003408301],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8245145,0.0002048905,0.003952549,0.05824431,0.002426374,0.001678293,0.000400624,0.0001991761,0.1083793],"genre_scores_gemma":[0.9943935,0.00001976695,0.00126447,0.0003069742,0.0000648686,0.00001158121,6.593079e-7,0.000007325316,0.003930863],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5933607,"threshold_uncertainty_score":0.7784196,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3097609978046282,"score_gpt":0.4126229492891771,"score_spread":0.1028619514845489,"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."}}