{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T12:09:13Z","timestamp":1767182953887,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,27]],"date-time":"2024-04-27T00:00:00Z","timestamp":1714176000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100002920","name":"Research Grants Council, University Grants Committee","doi-asserted-by":"publisher","award":["GRF 11209520","CRF C7004-22G"],"award-info":[{"award-number":["GRF 11209520","CRF C7004-22G"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,27]]},"DOI":"10.1145\/3620665.3640353","type":"proceedings-article","created":{"date-parts":[[2024,4,22]],"date-time":"2024-04-22T14:18:06Z","timestamp":1713795486000},"page":"830-845","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Palantir: Hierarchical Similarity Detection for Post-Deduplication Delta Compression"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5531-474X","authenticated-orcid":false,"given":"Hongming","family":"Huang","sequence":"first","affiliation":[{"name":"City University of Hong Kong, Hong Kong, Hong Kong"},{"name":"Huawei Technologies, Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4008-1963","authenticated-orcid":false,"given":"Peng","family":"Wang","sequence":"additional","affiliation":[{"name":"Huawei Technologies, Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4482-6248","authenticated-orcid":false,"given":"Qiang","family":"Su","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9359-9571","authenticated-orcid":false,"given":"Hong","family":"Xu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6431-9868","authenticated-orcid":false,"given":"Chun Jason","family":"Xue","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence, Masdar City, Abu Dhabi, United Arab Emirates"},{"name":"City University of Hong Kong, Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3083-2775","authenticated-orcid":false,"given":"Andr\u00e9","family":"Brinkmann","sequence":"additional","affiliation":[{"name":"Johannes Gutenberg University Mainz, Mainz, Germany"}]}],"member":"320","published-online":{"date-parts":[[2024,4,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/1534530.1534539"},{"key":"e_1_3_2_1_2_1","volume-title":"USENIX Annual Technical Conference (ATC)","author":"Black John","year":"2006","unstructured":"John Black. Compare-by-hash: A reasoned analysis. In USENIX Annual Technical Conference (ATC), Boston, MA, USA, May 30 - June 3, pages 85--90, 2006."},{"key":"e_1_3_2_1_3_1","first-page":"21","volume-title":"Compression and Complexity of Sequences (SEQUENCES)","author":"Broder Andrei Z","year":"1997","unstructured":"Andrei Z Broder. On the resemblance and containment of documents. In Compression and Complexity of Sequences (SEQUENCES), pages 21--29, 1997."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45123-4_1"},{"key":"e_1_3_2_1_5_1","first-page":"124","article-title":"A block-sorting lossless data compression algorithm","author":"Burrows Michael","year":"1994","unstructured":"Michael Burrows. A block-sorting lossless data compression algorithm. SRC Research Report, 124, 1994.","journal-title":"SRC Research Report"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the USENIX Annual Technical Conference (ATC), June 9-14","author":"Douglis Fred","year":"2003","unstructured":"Fred Douglis and Arun Iyengar. Application-specific delta-encoding via resemblance detection. In Proceedings of the USENIX Annual Technical Conference (ATC), June 9-14, San Antonio, Texas, USA, pages 113--126. USENIX, 2003."},{"key":"e_1_3_2_1_7_1","volume-title":"7th USENIX Conference on File and Storage Technologies (FAST)","author":"Dubnicki Cezary","year":"2009","unstructured":"Cezary Dubnicki, Leszek Gryz, Lukasz Heldt, Michal Kaczmarczyk, Wojciech Kilian, Przemyslaw Strzelczak, Jerzy Szczepkowski, Cristian Ungureanu, and Michal Welnicki. Hydrastor: A scalable secondary storage. In 7th USENIX Conference on File and Storage Technologies (FAST), February 24-27, 2009, San Francisco, CA, USA, pages 197--210, 2009."},{"key":"e_1_3_2_1_8_1","volume-title":"USENIX Annual Technical Conference (ATC)","author":"El-Shimi Ahmed","year":"2012","unstructured":"Ahmed El-Shimi, Ran Kalach, Ankit Kumar, Adi Ottean, Jin Li, and Sudipta Sengupta. Primary data deduplication - large scale study and system design. In USENIX Annual Technical Conference (ATC), Boston, MA, USA, June 13-15, pages 285--296, 2012."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2011.20"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2741948.2741952"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/DCC.2012.44"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/1247415.1247420"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2019.00102"},{"key":"e_1_3_2_1_14_1","volume-title":"7th USENIX Conference on File and Storage Technologies (FAST)","author":"Lillibridge Mark","year":"2009","unstructured":"Mark Lillibridge, Kave Eshghi, Deepavali Bhagwat, Vinay Deolalikar, Greg Trezis, and Peter Camble. Sparse indexing: Large scale, inline deduplication using sampling and locality. In 7th USENIX Conference on File and Storage Technologies (FAST), February 24-27, 2009, San Francisco, CA, USA, pages 111--123, 2009."},{"key":"e_1_3_2_1_15_1","volume-title":"12th USENIX Conference on File and Storage Technologies (FAST)","author":"Lin Xing","year":"2014","unstructured":"Xing Lin, Guanlin Lu, Fred Douglis, Philip Shilane, and Grant Wallace. Migratory compression: coarse-grained data reordering to improve compressibility. In 12th USENIX Conference on File and Storage Technologies (FAST), Santa Clara, CA, USA, February 17-20, pages 257--271, 2014."},{"key":"e_1_3_2_1_16_1","unstructured":"Joshua P. MacDonald. File system support for delta compression. http:\/\/www.xmailserver.com\/xdfs.pdf 2000."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/1534530.1534541"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/2591272.2591291"},{"key":"e_1_3_2_1_19_1","volume-title":"A study of practical deduplication. ACM Transactions on Storage (ToS), 7(4):14:1--14:20","author":"Meyer Dutch T.","year":"2012","unstructured":"Dutch T. Meyer and William J. Bolosky. A study of practical deduplication. ACM Transactions on Storage (ToS), 7(4):14:1--14:20, 2012."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/502034.502052"},{"key":"e_1_3_2_1_21_1","volume-title":"20th USENIX Conference on File and Storage Technologies (FAST)","author":"Park Jisung","year":"2022","unstructured":"Jisung Park, Jeonggyun Kim, Yeseong Kim, Sungjin Lee, and Onur Mutlu. Deepsketch: A new machine learning-based reference search technique for post-deduplication delta compression. In 20th USENIX Conference on File and Storage Technologies (FAST), Santa Clara, CA, USA, February 22-24, pages 247--264, 2022."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.5555\/1247415.1247421"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"e_1_3_2_1_25_1","volume-title":"Wan-optimized replication of backup datasets using stream-informed delta compression. ACM Transactions on Storage (ToS), 8(4):13:1--13:26","author":"Shilane Philip","year":"2012","unstructured":"Philip Shilane, Mark Huang, Grant Wallace, and Windsor Hsu. Wan-optimized replication of backup datasets using stream-informed delta compression. ACM Transactions on Storage (ToS), 8(4):13:1--13:26, 2012."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.5555\/2342806.2342816"},{"key":"e_1_3_2_1_27_1","volume-title":"10th USENIX Conference on File and Storage Technologies (FAST)","author":"Srinivasan Kiran","year":"2012","unstructured":"Kiran Srinivasan, Timothy Bisson, Garth R. Goodson, and Kaladhar Voruganti. idedup: latency-aware, inline data deduplication for primary storage. In 10th USENIX Conference on File and Storage Technologies (FAST), San Jose, CA, USA, February 14-17, page 24, 2012."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/2208461.2208465"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2015.2456015"},{"key":"e_1_3_2_1_30_1","volume-title":"USENIX Annual Technical Conference (ATC)","author":"Xia Wen","year":"2016","unstructured":"Wen Xia, Yukun Zhou, Hong Jiang, Dan Feng, Yu Hua, Yuchong Hu, Liu, and Yucheng Zhang. Fastcdc: a fast and efficient content-defined chunking approach for data deduplication. In USENIX Annual Technical Conference (ATC), Denver, CO, USA, June 22-24, pages 101--114, 2016."},{"key":"e_1_3_2_1_31_1","volume-title":"17th USENIX Conference on File and Storage Technologies (FAST)","author":"Zhang Yucheng","year":"2019","unstructured":"Yucheng Zhang, Wen Xia, Dan Feng, Hong Jiang, Yu Hua, and Qiang Wang. Finesse: Fine-grained feature locality based fast resemblance detection for post-deduplication delta compression. In 17th USENIX Conference on File and Storage Technologies (FAST), Boston, MA, February 25-28, pages 121--128, 2019."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/1364813.1364831"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1978.1055934"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE51399.2021.00048"},{"key":"e_1_3_2_1_35_1","volume-title":"USENIX Annual Technical Conference (ATC)","author":"Zou Xiangyu","year":"2022","unstructured":"Xiangyu Zou, Wen Xia, Philip Shilane, Haijun Zhang, and Xuan Wang. Building a high-performance fine-grained deduplication framework for backup storage with high deduplication ratio. In USENIX Annual Technical Conference (ATC), Carlsbad, CA, USA, July 11-13, pages 19--36, 2022."}],"event":{"name":"ASPLOS '24: 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","SIGOPS ACM Special Interest Group on Operating Systems","SIGPLAN ACM Special Interest Group on Programming Languages","SIGBED ACM Special Interest Group on Embedded Systems"],"location":"La Jolla CA USA","acronym":"ASPLOS '24"},"container-title":["Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3620665.3640353","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3620665.3640353","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:29:27Z","timestamp":1750285767000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3620665.3640353"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,27]]},"references-count":34,"alternative-id":["10.1145\/3620665.3640353","10.1145\/3620665"],"URL":"https:\/\/doi.org\/10.1145\/3620665.3640353","relation":{},"subject":[],"published":{"date-parts":[[2024,4,27]]},"assertion":[{"value":"2024-04-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}