{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:56:30Z","timestamp":1780588590788,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":9,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,6,25]],"date-time":"2019-06-25T00:00:00Z","timestamp":1561420800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,6,25]]},"DOI":"10.1145\/3299869.3320210","type":"proceedings-article","created":{"date-parts":[[2019,6,18]],"date-time":"2019-06-18T17:41:43Z","timestamp":1560879703000},"page":"1993-1996","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":16,"title":["Unit Testing Data with Deequ"],"prefix":"10.1145","author":[{"given":"Sebastian","family":"Schelter","sequence":"first","affiliation":[{"name":"Amazon Research, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felix","family":"Biessmann","sequence":"additional","affiliation":[{"name":"Amazon Research, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dustin","family":"Lange","sequence":"additional","affiliation":[{"name":"Amazon Research, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tammo","family":"Rukat","sequence":"additional","affiliation":[{"name":"Amazon Research, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Phillipp","family":"Schmidt","sequence":"additional","affiliation":[{"name":"Amazon Research, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephan","family":"Seufert","sequence":"additional","affiliation":[{"name":"Amazon Research, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pierre","family":"Brunelle","sequence":"additional","affiliation":[{"name":"Amazon Research, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrey","family":"Taptunov","sequence":"additional","affiliation":[{"name":"Amazon Research, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2019,6,25]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Michael Armbrust Reynold S Xin Cheng Lian Yin Huai Davies Liu Joseph K Bradley Xiangrui Meng Tomer Kaftan Michael J Franklin Ali Ghodsi etal 2015. Spark sql: Relational data processing in spark. SIGMOD (2015) 1383--1394.  Michael Armbrust Reynold S Xin Cheng Lian Yin Huai Davies Liu Joseph K Bradley Xiangrui Meng Tomer Kaftan Michael J Franklin Ali Ghodsi et al. 2015. Spark sql: Relational data processing in spark. SIGMOD (2015) 1383--1394.","DOI":"10.1145\/2723372.2742797"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.14778\/3137765.3137775"},{"key":"e_1_3_2_1_3_1","volume-title":"Quantitative data cleaning for large databases. United Nations Economic Commission for Europe","author":"Hellerstein Joseph M","year":"2008","unstructured":"Joseph M Hellerstein . 2008. Quantitative data cleaning for large databases. United Nations Economic Commission for Europe ( 2008 ). Joseph M Hellerstein. 2008. Quantitative data cleaning for large databases. United Nations Economic Commission for Europe (2008)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3054782"},{"key":"e_1_3_2_1_5_1","unstructured":"Sebastian Schelter Felix Biessmann Tim Januschowski David Salinas Stephan Seufert Gyuri Szarvas etal 2018. On Challenges in Machine Learning Model Management. IEEE Data Engineering Bulletin (2018).  Sebastian Schelter Felix Biessmann Tim Januschowski David Salinas Stephan Seufert Gyuri Szarvas et al. 2018. On Challenges in Machine Learning Model Management. IEEE Data Engineering Bulletin (2018)."},{"key":"e_1_3_2_1_6_1","volume-title":"Automating Large-Scale Data Quality Verification. PVLDB 11, 12","author":"Schelter Sebastian","year":"2018","unstructured":"Sebastian Schelter , Dustin Lange , Philipp Schmidt , Meltem Celikel , Felix Biessmann , and Andreas Grafberger . 2018. Automating Large-Scale Data Quality Verification. PVLDB 11, 12 ( 2018 ). Sebastian Schelter, Dustin Lange, Philipp Schmidt, Meltem Celikel, Felix Biessmann, and Andreas Grafberger. 2018. Automating Large-Scale Data Quality Verification. PVLDB 11, 12 (2018)."},{"key":"e_1_3_2_1_7_1","volume-title":"Differential Data Quality Verification on Partitioned Data. ICDE","author":"Schelter Sebastian","year":"2019","unstructured":"Sebastian Schelter , Dustin Lange , Philipp Schmidt , Meltem Celikel , Felix Biessmann , and Andreas Grafberger . 2019. Differential Data Quality Verification on Partitioned Data. ICDE ( 2019 ). Sebastian Schelter, Dustin Lange, Philipp Schmidt, Meltem Celikel, Felix Biessmann, and Andreas Grafberger. 2019. Differential Data Quality Verification on Partitioned Data. ICDE (2019)."},{"key":"e_1_3_2_1_8_1","volume-title":"Hidden technical debt in machine learning systems. NeurIPS","author":"Sculley D","year":"2015","unstructured":"D Sculley , Gary Holt , Daniel Golovin , Eugene Davydov , Todd Phillips , Dietmar Ebner , Vinay Chaudhary , Michael Young , Jean-Francois Crespo , and Dan Dennison . 2015. Hidden technical debt in machine learning systems. NeurIPS ( 2015 ), 2503--2511. D Sculley, Gary Holt, Daniel Golovin, Eugene Davydov, Todd Phillips, Dietmar Ebner, Vinay Chaudhary, Michael Young, Jean-Francois Crespo, and Dan Dennison. 2015. Hidden technical debt in machine learning systems. NeurIPS (2015), 2503--2511."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.6.3.324"}],"event":{"name":"SIGMOD\/PODS '19: International Conference on Management of Data","location":"Amsterdam Netherlands","acronym":"SIGMOD\/PODS '19","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 2019 International Conference on Management of Data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3299869.3320210","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3299869.3320210","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:43:22Z","timestamp":1750207402000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3299869.3320210"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6,25]]},"references-count":9,"alternative-id":["10.1145\/3299869.3320210","10.1145\/3299869"],"URL":"https:\/\/doi.org\/10.1145\/3299869.3320210","relation":{},"subject":[],"published":{"date-parts":[[2019,6,25]]},"assertion":[{"value":"2019-06-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}