{"id":"W2542250253","doi":"10.1145/3012004","title":"The Challenge of Test Data Quality in Data Processing","year":2017,"lang":"en","type":"article","venue":"Journal of Data and Information Quality","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Vienna Science and Technology Fund","keywords":"Citation; Test (biology); Computer science; Data quality; Library science; Quality (philosophy); World Wide Web; Data science; Engineering; Operations management","routes":{"ca_aff":true,"ca_fund":true,"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","scholarly_communication","open_science"],"consensus_categories":["metaresearch","scholarly_communication","open_science"],"category_scores_codex":[0.07684713,0.00009933436,0.0003788442,0.000132241,0.0004888876,0.001588811,0.01318193,0.00005144603,0.00002323427],"category_scores_gemma":[0.05005168,0.00005754457,0.0000218084,0.0001495291,0.0003019364,0.04817026,0.00825838,0.0002452292,0.00001239321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001384224,"about_ca_system_score_gemma":0.0001956231,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002340162,"about_ca_topic_score_gemma":0.0008734395,"domain_scores_codex":[0.9943293,0.000458429,0.003107767,0.0002626484,0.001677534,0.0001642592],"domain_scores_gemma":[0.9806765,0.002355112,0.006202887,0.01011992,0.0005444069,0.0001012007],"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":[0.0001138698,0.0001372191,0.009313148,0.0001532511,0.00002424251,0.000001029494,0.001212401,0.000001661702,0.000003790228,0.008940975,0.03732755,0.9427708],"study_design_scores_gemma":[0.0008729789,0.00004662225,0.2072715,0.00009409866,0.00001942664,0.000004727925,0.007105169,0.006788434,0.000004392203,0.00884197,0.7688248,0.0001258078],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.1805124,0.007650509,0.2061564,0.407966,0.004576495,0.002813901,0.1164618,0.00007585327,0.07378659],"genre_scores_gemma":[0.9935477,0.002140949,0.002447961,0.0004336482,0.0001307293,6.512998e-7,0.001232431,0.000003363466,0.00006259493],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9426451,"threshold_uncertainty_score":0.9997627,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6182808189797534,"score_gpt":0.5581897740451959,"score_spread":0.06009104493455752,"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."}}