{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T03:15:37Z","timestamp":1752549337492,"version":"3.28.0"},"reference-count":37,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,5]]},"DOI":"10.1109\/icdew.2016.7495609","type":"proceedings-article","created":{"date-parts":[[2016,6,25]],"date-time":"2016-06-25T07:59:23Z","timestamp":1466841563000},"page":"12-19","source":"Crossref","is-referenced-by-count":3,"title":["High variety cloud databases"],"prefix":"10.1109","author":[{"given":"Shrainik","family":"Jain","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dominik","family":"Moritz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bill","family":"Howe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Data curation at scale: The data tamer system","author":"stonebraker","year":"2013","journal-title":"CIDR"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1145\/1807167.1807285"},{"key":"ref31","article-title":"Don't trash your intermediate results, cache'em","author":"roy","year":"2000","journal-title":"Arxiv preprint cs\/0203020"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1145\/2038916.2038925"},{"year":"2011","author":"zikopoulos","journal-title":"Understanding Big Data Analytics for Enterprise Class Hadoop and Streaming Data","key":"ref37"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1109\/TVCG.2015.2467191"},{"key":"ref35","first-page":"18","article-title":"Benchmarking amazon ec2 for high-performance scientific computing","volume":"33","author":"walker","year":"2008","journal-title":"USENIX login"},{"key":"ref34","volume":"3","author":"taleb","year":"2012","journal-title":"Antifragile Things That Gain from Disorder"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.14778\/2824032.2824098"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1145\/1107499.1107502"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1145\/2463676.2463712"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1145\/1807167.1807286"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1145\/2588555.2594530"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1007\/978-3-642-22351-8_31"},{"key":"ref16","article-title":"Sqlshare: Scientific workflow via relational view sharing","volume":"15","author":"howe","year":"2013","journal-title":"Computing in Science & Engineering Special Issue on Science Data Management"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1145\/2882903.2882957"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1145\/1978942.1979444"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/TVCG.2012.219"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.14778\/2732240.2732250"},{"key":"ref4","article-title":"Datahub: Collaborative data science & dataset version management at scale","author":"bhardwaj","year":"2014","journal-title":"CoRR abs\/1409 0798"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.14778\/2732279.2732282"},{"year":"0","journal-title":"Statist","key":"ref3"},{"year":"2008","journal-title":"TPC-H Benchmark Specification","key":"ref6"},{"year":"2012","author":"patil","journal-title":"Data Jujitsu The Art of Turning Data Into Product","key":"ref29"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1145\/1376616.1376746"},{"key":"ref8","article-title":"How ‘big data’ is different","volume":"54","author":"davenport","year":"2013","journal-title":"MIT Sloan Management Review"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.14778\/1938545.1938547"},{"year":"0","journal-title":"Sloan digital sky survey SkyServer","key":"ref2"},{"year":"0","journal-title":"OpenRefine (formerly google refine)","key":"ref1"},{"key":"ref9","first-page":"83","article-title":"Semantic integration research in the database community: A brief survey","volume":"26","author":"doan","year":"2005","journal-title":"AI Magazine"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1007\/978-94-011-0946-8_6"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.14778\/1880172.1880175"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1145\/2213836.2213931"},{"key":"ref24","article-title":"3d data management: Controlling data volume, velocity and variety","volume":"6","author":"laney","year":"2001","journal-title":"META Group ResearchNote"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1145\/2213836.2213840"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/MIC.2012.50"},{"key":"ref25","article-title":"For big-data scientists, ‘janitor work’ is key hurdle to insights","author":"lohr","year":"2014","journal-title":"New York Times"}],"event":{"name":"2016 IEEE 32nd International Conference on Data Engineering Workshops (ICDEW)","start":{"date-parts":[[2016,5,16]]},"location":"Helsinki, Finland","end":{"date-parts":[[2016,5,20]]}},"container-title":["2016 IEEE 32nd International Conference on Data Engineering Workshops (ICDEW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7491933\/7495596\/07495609.pdf?arnumber=7495609","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2016,9,29]],"date-time":"2016-09-29T10:57:30Z","timestamp":1475146650000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7495609\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,5]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icdew.2016.7495609","relation":{},"subject":[],"published":{"date-parts":[[2016,5]]}}}