{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:24:27Z","timestamp":1787012667905,"version":"3.56.0"},"reference-count":41,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009,9]]},"DOI":"10.1109\/mascot.2009.5366623","type":"proceedings-article","created":{"date-parts":[[2010,1,7]],"date-time":"2010-01-07T11:43:14Z","timestamp":1262864594000},"page":"1-9","source":"Crossref","is-referenced-by-count":226,"title":["Extreme Binning: Scalable, parallel deduplication for chunk-based file backup"],"prefix":"10.1109","author":[{"given":"D.","family":"Bhagwat","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"K.","family":"Eshghi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"D.D.E.","family":"Long","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"M.","family":"Lillibridge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"19","article-title":"Understanding data deduplication ratios","author":"dutch","year":"2008","journal-title":"Data Management Forum"},{"key":"35","doi-asserted-by":"publisher","DOI":"10.1145\/1534530.1534539"},{"key":"17","article-title":"Secure hash standard","year":"0","journal-title":"FIPS 180-2"},{"key":"36","doi-asserted-by":"publisher","DOI":"10.1145\/1060289.1060316"},{"key":"18","first-page":"73","article-title":"Alternatives for detecting redundancy in storage systems data","author":"policroniades","year":"2004","journal-title":"Proceedings of the General Track 2004 USENIX Annual Technical Conference"},{"key":"33","doi-asserted-by":"publisher","DOI":"10.1145\/567112.567116"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.17487\/rfc1321"},{"key":"34","first-page":"113","article-title":"Application-specific delta-encoding via resemblance detection","author":"douglis","year":"2003","journal-title":"Proceedings of the 2003 USENIX Annual Technical Conference"},{"key":"16","article-title":"Secure hash standard","year":"0","journal-title":"FIPS 180-2"},{"key":"39","doi-asserted-by":"publisher","DOI":"10.1145\/383059.383071"},{"key":"13","first-page":"123","article-title":"Jumbo Store: Providing efficient incremental upload and versioning for a utility rendering service","author":"eshghi","year":"2007","journal-title":"Proc USENIX Conf File and Storage Technologies (FAST)"},{"key":"14","article-title":"Fingerprinting by random polynomials","author":"rabin","year":"1981"},{"key":"37","doi-asserted-by":"publisher","DOI":"10.1145\/378993.379239"},{"key":"11","first-page":"143","article-title":"Fast, inexpensive content-addressed storage in Foundation","author":"rhea","year":"2008","journal-title":"Proceedings of the 2008 USENIX Annual Technical Conference"},{"key":"38","doi-asserted-by":"publisher","DOI":"10.1109\/HOTOS.2001.990064"},{"key":"12","first-page":"129","article-title":"Shark: Scaling file servers via cooperative caching","author":"annapureddy","year":"2005","journal-title":"Proceedings of the 2nd Symposium on Networked Systems Design and Implementation (NSDI)"},{"key":"21","first-page":"547","article-title":"E?tude comparative de la distribution orale dans une portion des Alpes et des Jura","volume":"37","author":"jaccard","year":"1901","journal-title":"Bulletin del la Socie?te? Vaudoise des Sciences Naturelles"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1109\/SEQUEN.1997.666900"},{"key":"41","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2003.818784"},{"key":"40","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45518-3_18"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1145\/1281192.1281207"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2004.1303042"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.1145\/236711.236713"},{"key":"25","author":"eshghi","year":"2005","journal-title":"A framework for analyzing and improving content-based chunking algorithms"},{"key":"26","first-page":"13","article-title":"An analysis of compare-by-hash","author":"henson","year":"2003","journal-title":"Proceedings of the 9th Workshop on Hot Topics in Operating Systems (HotOS-IX)"},{"key":"27","first-page":"85","article-title":"Compare-by-hash: A reasoned analysis","author":"black","year":"2006","journal-title":"Proceedings of the Systems and Experience Track 2006 USENIX Annual Technical Conference"},{"key":"28","year":"0","journal-title":"Oracle Berkeley DB"},{"key":"29","doi-asserted-by":"publisher","DOI":"10.1145\/362686.362692"},{"key":"3","article-title":"107th Congress, United States of America. Public Law 107-204: Sarbanes-Oxley Act of 2002","year":"2002"},{"key":"2","article-title":"104th Congress, United States of America. Public Law 104-191: Health Insurance Portability and Accountability Act (HIPAA)","year":"1996"},{"key":"10","first-page":"111","article-title":"Sparse Indexing: Large scale, inline deduplication using sampling and locality","author":"lillibridge","year":"2009","journal-title":"Proc USENIX Conf File and Storage Technologies (FAST)"},{"key":"1","author":"gantz","year":"2008","journal-title":"The Diverse and Exploding Digital Universe An Updated Forecast of Worldwide Information Growth Through 2011"},{"key":"30","article-title":"Decentralized deduplication in SAN cluster file systems","author":"clements","year":"2009","journal-title":"Proceedings of the 2009 USENIX Annual Technical Conference"},{"key":"7","first-page":"89","article-title":"Venti: A new approach to archival storage","author":"quinlan","year":"2002","journal-title":"Proc USENIX Conf File and Storage Technologies (FAST)"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1145\/502034.502052"},{"key":"32","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2005.47"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1145\/1081870.1081916"},{"key":"31","year":"2002","journal-title":"EMC Centera Content Addressed Storage System Data Sheet"},{"key":"4","article-title":"Experiencing Data De-Duplication: Improving Efficiency and Reducing Capacity Requirements","author":"biggar","year":"2007","journal-title":"The Enterprise Strategy Group"},{"key":"9","first-page":"269","article-title":"Avoiding the disk bottleneck in the data domain deduplication file system","author":"zhu","year":"2008","journal-title":"Proceedings of the USENIX Conference on File and Storage Technonologies (FAST)"},{"key":"8","year":"0"}],"event":{"name":"amp; Simulation of Computer and Telecommunication Systems (MASCOTS)","location":"London","start":{"date-parts":[[2009,9,21]]},"end":{"date-parts":[[2009,9,23]]}},"container-title":["2009 IEEE International Symposium on Modeling, Analysis &amp; Simulation of Computer and Telecommunication Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5353818\/5362673\/05366623.pdf?arnumber=5366623","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,18]],"date-time":"2017-03-18T23:01:17Z","timestamp":1489878077000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5366623\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,9]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/mascot.2009.5366623","relation":{},"subject":[],"published":{"date-parts":[[2009,9]]}}}