{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T16:21:46Z","timestamp":1774282906946,"version":"3.50.1"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000993","name":"Battelle","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000993","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,15]]},"DOI":"10.1109\/bigdata52589.2021.9671534","type":"proceedings-article","created":{"date-parts":[[2022,1,13]],"date-time":"2022-01-13T20:39:16Z","timestamp":1642106356000},"page":"4643-4651","source":"Crossref","is-referenced-by-count":28,"title":["A Lakehouse Architecture for the Management and Analysis of Heterogeneous Data for Biomedical Research and Mega-biobanks"],"prefix":"10.1109","author":[{"given":"Edmon","family":"Begoli","sequence":"first","affiliation":[]},{"given":"Ian","family":"Goethert","sequence":"additional","affiliation":[]},{"given":"Kathryn","family":"Knight","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMlim035027"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1177\/019384102236520"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1126\/science.aab2374"},{"key":"ref13","author":"winkler","year":"1999","journal-title":"The State of Record Linkage and Current Research Problems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2934664"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415560"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93414-3_7"},{"key":"ref17","article-title":"Comparison of different imputation methods","author":"johnston","year":"2011","journal-title":"INTERBULL Bulletin"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2015.04.108"},{"key":"ref19","article-title":"Prov implementation report","author":"huynh","year":"2013"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/sdata.2016.18","article-title":"The fair guiding principles for scientific data management and stewardship","volume":"3","author":"wilkinson","year":"2016","journal-title":"Scientific Data"},{"key":"ref3","article-title":"Lakehouse: A new generation of open platforms that unify data warehousing and advanced analytics","author":"armbrust","year":"2021","journal-title":"CIDR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-62703-447-0_8"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btr330"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-2337-6_15"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-2199-0_8"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2015.09.016"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1097\/GIM.0b013e3180330039"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11235-009-9248-8"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1287\/educ.2016.0143"}],"event":{"name":"2021 IEEE International Conference on Big Data (Big Data)","location":"Orlando, FL, USA","start":{"date-parts":[[2021,12,15]]},"end":{"date-parts":[[2021,12,18]]}},"container-title":["2021 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9671263\/9671273\/09671534.pdf?arnumber=9671534","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:55:28Z","timestamp":1652201728000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9671534\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,15]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/bigdata52589.2021.9671534","relation":{},"subject":[],"published":{"date-parts":[[2021,12,15]]}}}