{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006992122,0.001668055,0.002517763,0.003499607,0.001923424,0.004078868,0.00368711,0.002409547,0.001696217],"category_scores_gemma":[0.02807941,0.001245458,0.002118364,0.004322083,0.002369594,0.007502197,0.007562257,0.00319262,0.0003325418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001042516,"about_ca_system_score_gemma":0.002741166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003126073,"about_ca_topic_score_gemma":0.005211889,"domain_scores_codex":[0.9887955,0.00341729,0.001016295,0.002896592,0.003378685,0.0004956144],"domain_scores_gemma":[0.9780578,0.009552233,0.003059195,0.00701956,0.001844653,0.0004666693],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006010964,0.0003340657,0.02491225,0.002080756,0.0007303224,0.002226294,0.004358881,0.1710988,0.0150146,0.1010663,0.01086256,0.666714],"study_design_scores_gemma":[0.00007194716,0.0003581979,0.008437688,0.0009594062,0.0008135459,0.002991155,0.003360111,0.5753628,0.03608993,0.3038822,0.0673245,0.0003485808],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04193952,0.002458528,0.948595,0.001295664,0.0001691789,0.0002161288,0.0004692852,0.002642501,0.002214246],"genre_scores_gemma":[0.3067697,0.0009069095,0.6892831,0.0005319891,0.0001041113,0.0001204977,0.0008393391,0.0005062603,0.0009380996],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9930079,"threshold_uncertainty_score":0.0369783,"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."}}