{"id":"W2044469685","doi":"10.1109/icde.2013.6544847","title":"Holistic data cleaning: Putting violations into context","year":2013,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":319,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Rotation formalisms in three dimensions; Hypergraph; Context (archaeology); Pipeline (software); Exploit; Reachability; Quality (philosophy); Functional dependency; Theoretical computer science; Isolation (microbiology); Data mining; Machine learning; Programming language; Relational database; Computer security","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002758085,0.00007419258,0.0001302318,0.0001138009,0.0002115692,0.0008685137,0.00190413,0.00002547938,0.006099558],"category_scores_gemma":[0.005692525,0.00005210497,0.00002422498,0.00035332,0.00006355769,0.00164673,0.001551356,0.00006790922,0.01238832],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001278677,"about_ca_system_score_gemma":0.00001999603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001971473,"about_ca_topic_score_gemma":0.0007005745,"domain_scores_codex":[0.9981281,0.0001248569,0.000472425,0.0004605473,0.0006456053,0.0001684577],"domain_scores_gemma":[0.9967242,0.001097134,0.0001198146,0.001807535,0.0001555115,0.0000958197],"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":[6.514601e-7,0.00002196083,0.0006453118,0.000001839727,0.000006768882,6.563137e-7,0.0002747285,0.000007747453,0.0000272931,0.110112,0.4408453,0.4480558],"study_design_scores_gemma":[0.000169716,0.00001735289,0.01181123,0.000008414145,0.00001014153,9.834822e-7,0.01106392,0.03846326,0.00001726674,0.2345692,0.7037352,0.0001333141],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02425549,0.00006405136,0.7437891,0.01946859,0.0008219974,0.0006123584,0.00007711017,0.0002152282,0.2106961],"genre_scores_gemma":[0.9723129,0.000002697299,0.01464895,0.002547231,0.00006755761,0.000008029888,0.00008594676,0.000004720801,0.01032198],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9480574,"threshold_uncertainty_score":0.994809,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5895766416565716,"score_gpt":0.5011305017614565,"score_spread":0.08844613989511518,"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."}}