{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:07:44Z","timestamp":1755839264801,"version":"3.37.3"},"reference-count":33,"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\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","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\/bigdata52589.2021.9671595","type":"proceedings-article","created":{"date-parts":[[2022,1,13]],"date-time":"2022-01-13T20:39:16Z","timestamp":1642106356000},"page":"2400-2405","source":"Crossref","is-referenced-by-count":2,"title":["Zero-Cost, Arrow-Enabled Data Interface for Apache Spark"],"prefix":"10.1109","author":[{"given":"Sebastiaan Alvarez","family":"Rodriguez","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jayjeet","family":"Chackrabroty","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aaron","family":"Chu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ivo","family":"Jimenez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeff","family":"LeFevre","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carlos","family":"Maltzahn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexandru","family":"Uta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"year":"0","key":"ref33","article-title":"Databricks"},{"year":"0","key":"ref32","article-title":"Databricks"},{"year":"0","key":"ref31","article-title":"Databricks"},{"article-title":"Apache spark connector for mongodb","year":"0","author":"lawley","key":"ref30"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2742797"},{"journal-title":"MongoDB - The Definitive Guide Powerful and Scalable Data Storage","year":"2013","author":"chodorow","key":"ref11"},{"key":"ref12","article-title":"Introducing windows azure","author":"chappell","year":"2009","journal-title":"Tech Rep"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-2199-0_8"},{"year":"0","key":"ref14","article-title":"Apache orc - high-performance columnar storage for hadoop"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-013"},{"journal-title":"Version 7 10 0 (R2010a)","year":"2010","key":"ref16"},{"article-title":"Python","year":"1991","author":"van rossum","key":"ref17"},{"key":"ref18","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"12th USENIX Symposium on Operating Systems Design and Implementation ( OSDI 16)"},{"article-title":"cudf - gpu dataframes","year":"0","author":"community","key":"ref19"},{"article-title":"H5spark: bridging the i\/o gap between spark and scientific data formats on hpc systems","year":"2016","author":"liu","key":"ref28"},{"key":"ref4","article-title":"Apache flink: Stream and batch processing in a single engine","volume":"36","author":"carbone","year":"2015","journal-title":"Bulletin of the IEEE Computer Society Technical Committee on Data Engineering"},{"article-title":"univocity-parsers","year":"0","author":"univocity team","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2903741"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TEL-NET.2017.8343593"},{"key":"ref29","first-page":"615","article-title":"Albis: High-performance file format for big data systems","author":"trivedi","year":"2018","journal-title":"2018 USENIX Annual Technical Conference (USENIX ATC 18)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.14445\/22312803\/IJCTT-V19P103"},{"key":"ref8","first-page":"561","article-title":"Ray: A distributed framework for emerging ai applications","author":"moritz","year":"2018","journal-title":"Proceedings of the 13th USENIX Conference on Operating Systems Design and Implementation"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2013.2243535"},{"journal-title":"Hadoop","year":"0","key":"ref2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2484425.2484427"},{"key":"ref1","first-page":"95","article-title":"Spark: Cluster computing with working sets","volume":"10","author":"zaharia","year":"2010","journal-title":"HotCloud"},{"year":"0","key":"ref20"},{"year":"2021","key":"ref22","article-title":"Arrow-spark"},{"year":"2018","key":"ref21","article-title":"Apache arrow"},{"article-title":"Arrow-7808: [java][dataset] implement dataset java api by jni to c++","year":"0","author":"zhang","key":"ref24"},{"year":"2018","key":"ref23","article-title":"Apache arrow java implementation"},{"key":"ref26","first-page":"513","article-title":"Is big data performance reproducible in modern cloud networks?","author":"uta","year":"2020","journal-title":"17th USENIX Symposium on Networked Systems Design and Implementation ( NSDI 20)"},{"year":"0","key":"ref25","article-title":"Optimized analytics package for spark platform (oap)"}],"event":{"name":"2021 IEEE International Conference on Big Data (Big Data)","start":{"date-parts":[[2021,12,15]]},"location":"Orlando, FL, USA","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\/09671595.pdf?arnumber=9671595","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:55:35Z","timestamp":1652201735000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9671595\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,15]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/bigdata52589.2021.9671595","relation":{},"subject":[],"published":{"date-parts":[[2021,12,15]]}}}