{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T22:31:00Z","timestamp":1769034660738,"version":"3.49.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T00:00:00Z","timestamp":1763078400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T00:00:00Z","timestamp":1763078400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,11,14]]},"DOI":"10.1109\/cloudcom67567.2025.11331481","type":"proceedings-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T20:37:16Z","timestamp":1768941436000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["SemanticPrefetcher: Accelerate Data Lake Access with Semantics-Aware File Prefetching"],"prefix":"10.1109","author":[{"given":"Tianze","family":"Wang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University"}]},{"given":"Guanjie","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}]},{"given":"Mingyan","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}]},{"given":"Manqi","family":"Luo","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}]},{"given":"Mingchuan","family":"Zou","sequence":"additional","affiliation":[{"name":"University of Cambridge"}]},{"given":"Chen","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}]},{"given":"Minyi","family":"Guo","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}]}],"member":"263","reference":[{"key":"ref1","first-page":"103","article-title":"Cloudscape: A study of storage services in modern cloud architectures","volume-title":"23rd USENIX Conference on File and Storage Technologies (FAST 25)","author":"Satija"},{"key":"ref2","volume-title":"Amazon S3","year":"2025"},{"key":"ref3","volume-title":"Azure Blob","year":"2025"},{"key":"ref4","article-title":"An-alyzing and mitigating data stalls in dnn training","author":"Mohan","year":"2020","journal-title":"arXiv preprint"},{"key":"ref5","volume-title":"Alluxio","year":"2025"},{"key":"ref6","volume-title":"JuiceFS","year":"2025"},{"key":"ref7","volume-title":"Linux Readahead","year":"2025"},{"key":"ref8","first-page":"843","article-title":"Effectively prefetching remote mem-ory with leap","volume-title":"2020 USENIX Annual Technical Conference (USENIX ATC 20)","author":"Al Maruf"},{"key":"ref9","first-page":"173","article-title":"C-miner: Mining block correlations in storage systems","volume":"4","author":"Li","year":"2004","journal-title":"FAST"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3127479.3131210"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654070"},{"key":"ref12","volume-title":"OneFS File Prefetching","year":"2025"},{"key":"ref13","first-page":"199","article-title":"Analysis of {HDFS} under {HBase}: A facebook messages case study","author":"Harter","year":"2014","journal-title":"12th USENIX Confer-ence on File and Storage Technologies (FAST 14)"},{"key":"ref14","article-title":"Network requirements for resource disaggregation","author":"Gao","year":"2016","journal-title":"USENIX OSDI"},{"key":"ref15","article-title":"Systems for memory disaggregation: challenges & opportu-nities","author":"Yelam","year":"2022","journal-title":"arXiv preprint"},{"key":"ref16","volume-title":"Amazon File Cache","year":"2025"},{"key":"ref17","volume-title":"COVIDx CT","year":"2025"},{"key":"ref18","volume-title":"Anime Art","year":"2025"},{"key":"ref19","volume-title":"ImageNet 1K TFrecords","year":"2025"},{"key":"ref20","volume-title":"MushR","year":"2025"},{"key":"ref21","volume-title":"L3DAS23","year":"2025"},{"key":"ref22","volume-title":"taco- robot","year":"2025"},{"key":"ref23","volume-title":"JuiceFS Readahead","year":"2025"},{"key":"ref24","author":"Kroeger","year":"2001","journal-title":"Design and implementation of a predictive file prefetching algorithm"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2006.73"},{"key":"ref26","article-title":"The pile: An 800gb dataset of diverse text for language modeling","author":"Gao","year":"2020","journal-title":"arXiv preprint"},{"key":"ref27","volume-title":"Fashion Dataset","year":"2025"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3453688.3461492"}],"event":{"name":"2025 lEEE International Conference on Cloud Computing Technology and Science (CloudCom)","location":"Shenzhen, China","start":{"date-parts":[[2025,11,14]]},"end":{"date-parts":[[2025,11,16]]}},"container-title":["2025 lEEE International Conference on Cloud Computing Technology and Science (CloudCom)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11330195\/11331311\/11331481.pdf?arnumber=11331481","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T07:50:56Z","timestamp":1768981856000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11331481\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,14]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/cloudcom67567.2025.11331481","relation":{},"subject":[],"published":{"date-parts":[[2025,11,14]]}}}