{"id":"W2549035799","doi":"10.14778/3007263.3007320","title":"Qualitative data cleaning","year":2016,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Scripting language; Data quality; Data science; Analytics; Big data; Data mining; Qualitative property; Taxonomy (biology); Human error; Data analysis; Machine learning; Engineering; Reliability 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":[0.007971959,0.0001136126,0.0002105665,0.00009865779,0.0001230741,0.0001294311,0.003991697,0.00002597512,0.0002262752],"category_scores_gemma":[0.005384886,0.00004875302,0.00007263375,0.0004165528,0.0001901714,0.0009519894,0.003356651,0.00005801426,0.0002092324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004172901,"about_ca_system_score_gemma":0.000019799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004059124,"about_ca_topic_score_gemma":0.000009891659,"domain_scores_codex":[0.9970739,0.00005420314,0.0006099861,0.000517125,0.001516499,0.0002282369],"domain_scores_gemma":[0.9975797,0.0007566946,0.000523128,0.0007999892,0.0002778083,0.00006266577],"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":[0.00007424691,0.000152565,0.001240407,0.00003294626,0.00009278326,3.327538e-7,0.01012476,7.25488e-7,0.01998267,0.4476053,0.3827985,0.1378948],"study_design_scores_gemma":[0.001105763,0.0001219972,0.002702483,0.0002329907,0.00005607465,0.000003192875,0.04698891,0.00007014482,0.04455288,0.3912195,0.5126522,0.0002937953],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5305543,0.0003720428,0.01277398,0.1468504,0.002957273,0.002887454,0.001561246,0.000282114,0.3017612],"genre_scores_gemma":[0.9906567,0.00002967497,0.002062176,0.00046064,0.00006355929,0.00001402529,0.000001912362,0.000008211407,0.006703097],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4601024,"threshold_uncertainty_score":0.7417634,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4971943852757241,"score_gpt":0.5118316654115125,"score_spread":0.01463728013578841,"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."}}