{"id":"W2792572948","doi":"10.1145/3186549.3186559","title":"Data Quality","year":2018,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University of Waterloo","funders":"","keywords":"Computer science; Scope (computer science); Quality (philosophy); Data quality; Empiricism; Data science; Action (physics); Data mining; Epistemology; Programming language; 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":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.009842128,0.0001118675,0.0002354045,0.0001159824,0.0001903233,0.0003212033,0.007113324,0.00005492493,0.003440154],"category_scores_gemma":[0.01962369,0.00008181413,0.00004949893,0.000543984,0.000212694,0.0009450418,0.005003255,0.00009706799,0.008168026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001572625,"about_ca_system_score_gemma":0.00004029914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004326645,"about_ca_topic_score_gemma":0.002138969,"domain_scores_codex":[0.9966689,0.000426432,0.000677238,0.0008536921,0.001103173,0.0002705388],"domain_scores_gemma":[0.9894873,0.001685167,0.000241932,0.008265403,0.0002020653,0.0001181657],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002260922,0.0000391258,0.001671049,0.000002113307,0.00001158183,0.00000173286,0.00009111282,8.589792e-8,0.00004897045,0.005743865,0.5250216,0.4673462],"study_design_scores_gemma":[0.000150417,0.00006110441,0.008588974,0.000003802863,0.000006493947,7.016791e-7,0.000352305,0.0002051234,0.00007656476,0.1165323,0.8738972,0.0001249962],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4250788,0.0001892553,0.218871,0.05202212,0.01240181,0.001081529,0.002532732,0.0006020995,0.2872206],"genre_scores_gemma":[0.8986552,0.00005338884,0.0450939,0.008180683,0.001891306,0.00001502949,0.0003485813,0.00002713859,0.04573471],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4735765,"threshold_uncertainty_score":0.9982587,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6848192121373361,"score_gpt":0.55904053398058,"score_spread":0.1257786781567561,"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."}}