{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T05:10:09Z","timestamp":1746335409965,"version":"3.40.4"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319111933"},{"type":"electronic","value":"9783319111940"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-319-11194-0_11","type":"book-chapter","created":{"date-parts":[[2014,8,12]],"date-time":"2014-08-12T14:25:55Z","timestamp":1407853555000},"page":"136-149","source":"Crossref","is-referenced-by-count":2,"title":["Identifying File Similarity in Large Data Sets by Modulo File Length"],"prefix":"10.1007","author":[{"given":"Yongtao","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhui","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoguang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junjie","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"3","key":"11_CR1","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1145\/1288783.1288788","volume":"3","author":"N. Agrawal","year":"2007","unstructured":"Agrawal, N., Bolosky, W.J., Douceur, J.R., Lorch, J.R.: A five-year study of file-system metadata. ACM Transactions on Storage (TOS)\u00a03(3), 9 (2007)","journal-title":"ACM Transactions on Storage (TOS)"},{"key":"11_CR2","unstructured":"Baker, B.S.: On finding duplication and near-duplication in large software systems. In: Proceedings of 2nd Working Conference on Reverse Engineering,1995, pp. 86\u201395. IEEE (1995)"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Bhagwat, D., Eshghi, K., Long, D.D., Lillibridge, M.: Extreme binning: Scalable, parallel deduplication for chunk-based file backup. In: IEEE International Symposium on Modeling, Analysis & Simulation of Computer and Telecommunication Systems, MASCOTS 2009, pp. 1\u20139. IEEE (2009)","DOI":"10.1109\/MASCOT.2009.5366623"},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Biswas, S., Franklin, D., Savage, A., Dixon, R., Sherwood, T., Chong, F.T.: Multi-execution: Multicore caching for data-similar executions. In: ACM SIGARCH Computer Architecture News, vol.\u00a037, pp. 164\u2013173. ACM (2009)","DOI":"10.1145\/1555815.1555777"},{"issue":"2","key":"11_CR5","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1145\/319983.319987","volume":"8","author":"D. Bitton","year":"1983","unstructured":"Bitton, D., DeWitt, D.J.: Duplicate record elimination in large data files. ACM Transactions on Database Systems (TODS)\u00a08(2), 255\u2013265 (1983)","journal-title":"ACM Transactions on Database Systems (TODS)"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Brin, S., Davis, J., Garcia-Molina, H.: Copy detection mechanisms for digital documents. In: ACM SIGMOD Record, vol.\u00a024, pp. 398\u2013409. ACM (1995)","DOI":"10.1145\/568271.223855"},{"key":"11_CR7","unstructured":"Broder, A.Z.: On the resemblance and containment of documents. In: Proceedings of the Compression and Complexity of Sequences 1997, pp. 21\u201329. IEEE (1997)"},{"issue":"8","key":"11_CR8","doi-asserted-by":"publisher","first-page":"1157","DOI":"10.1016\/S0169-7552(97)00031-7","volume":"29","author":"A.Z. Broder","year":"1997","unstructured":"Broder, A.Z., Glassman, S.C., Manasse, M.S., Zweig, G.: Syntactic clustering of the web. Computer Networks and ISDN Systems\u00a029(8), 1157\u20131166 (1997)","journal-title":"Computer Networks and ISDN Systems"},{"issue":"1","key":"11_CR9","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1002\/(SICI)1097-4571(199401)45:1<12::AID-ASI2>3.0.CO;2-L","volume":"45","author":"M.K. Buckland","year":"1994","unstructured":"Buckland, M.K., Gey, F.C.: The relationship between recall and precision. JASIS\u00a045(1), 12\u201319 (1994)","journal-title":"JASIS"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Charikar, M.S.: Similarity estimation techniques from rounding algorithms. In: Proceedings of the Thiry-fourth Annual ACM Symposium on Theory of Computing, pp. 380\u2013388. ACM (2002)","DOI":"10.1145\/509961.509965"},{"issue":"SI","key":"11_CR11","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1145\/844128.844155","volume":"36","author":"L.P. Cox","year":"2002","unstructured":"Cox, L.P., Murray, C.D., Noble, B.D.: Pastiche: Making backup cheap and easy. ACM SIGOPS Operating Systems Review\u00a036(SI), 285\u2013298 (2002)","journal-title":"ACM SIGOPS Operating Systems Review"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Forman, G., Eshghi, K., Chiocchetti, S.: Finding similar files in large document repositories. In: Proceedings of the Eleventh ACM SIGKDD International Conference on Knowledge Discovery in Data Mining, pp. 394\u2013400. ACM (2005)","DOI":"10.1145\/1081870.1081916"},{"key":"11_CR13","unstructured":"Gens, F.: Top 10 predictions idc predictions Competing on the 3rd platform (2013), http:\/\/www.idc.com\/research\/Predictions13\/downloadable\/238044.pdf"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Hua, Y., Liu, X., Feng, D.: Data similarity-aware computation infrastructure for the cloud. IEEE Transactions on Computers p.\u00a01 (2013)","DOI":"10.1109\/TC.2013.111"},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"Indyk, P., Motwani, R.: Approximate nearest neighbors: towards removing the curse of dimensionality. In: Proceedings of the Thirtieth Annual ACM Symposium on Theory of Computing, pp. 604\u2013613. ACM (1998)","DOI":"10.1145\/276698.276876"},{"key":"11_CR16","unstructured":"Labs, F.: Tokyo cabinet, http:\/\/fallabs.com\/tokyocabinet\/"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Song, L., Deng, Y., Xie, J.: Exploiting fingerprint prefetching to improve the performance of data deduplication. In: Proceedings of the 15th IEEE International Conference on High Performance Computing and Communications. IEEE (2013)","DOI":"10.1109\/HPCC.and.EUC.2013.122"},{"key":"11_CR18","first-page":"1","volume":"94","author":"U. Manber","year":"1994","unstructured":"Manber, U., et al.: Finding similar files in a large file system. Usenix Winter\u00a094, 1\u201310 (1994)","journal-title":"Usenix Winter"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Manku, G.S., Jain, A., Das Sarma, A.: Detecting near-duplicates for web crawling. In: Proceedings of the 16th International Conference on World Wide Web, pp. 141\u2013150. ACM (2007)","DOI":"10.1145\/1242572.1242592"},{"issue":"4","key":"11_CR20","first-page":"14","volume":"7","author":"D.T. Meyer","year":"2012","unstructured":"Meyer, D.T., Bolosky, W.J.: A study of practical deduplication. ACM Transactions on Storage (TOS)\u00a07(4), 14 (2012)","journal-title":"ACM Transactions on Storage (TOS)"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Muthitacharoen, A., Chen, B., Mazieres, D.: A low-bandwidth network file system. In: ACM SIGOPS Operating Systems Review, vol.\u00a035, pp. 174\u2013187. ACM (2001)","DOI":"10.1145\/502059.502052"},{"key":"11_CR22","doi-asserted-by":"crossref","unstructured":"Ouyang, Z., Memon, N., Suel, T., Trendafilov, D.: Cluster-based delta compression of a collection of files. In: Proceedings of the Third International Conference on Web Information Systems Engineering, WISE 2002, pp. 257\u2013266. IEEE (2002)","DOI":"10.1109\/WISE.2002.1181662"},{"issue":"1","key":"11_CR23","first-page":"37","volume":"2","author":"D.M. Powers","year":"2011","unstructured":"Powers, D.M.: Evaluation: from precision, recall and f-measure to roc, informedness, markedness & correlation. Journal of Machine Learning Technologies\u00a02(1), 37\u201363 (2011)","journal-title":"Journal of Machine Learning Technologies"},{"key":"11_CR24","unstructured":"Quinlan, S., Dorward, S.: Venti: A new approach to archival storage. In: FAST, vol.\u00a02, pp. 89\u2013101 (2002)"},{"key":"11_CR25","unstructured":"Ruijter, M.: Lessfs, http:\/\/www.lessfs.com\/wordpress\/"},{"issue":"SI","key":"11_CR26","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1145\/844128.844163","volume":"36","author":"C.P. Sapuntzakis","year":"2002","unstructured":"Sapuntzakis, C.P., Chandra, R., Pfaff, B., Chow, J., Lam, M.S., Rosenblum, M.: Optimizing the migration of virtual computers. ACM SIGOPS Operating Systems Review\u00a036(SI), 377\u2013390 (2002)","journal-title":"ACM SIGOPS Operating Systems Review"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Shivakumar, N., Garcia-Molina, H.: Building a scalable and accurate copy detection mechanism. In: Proceedings of the First ACM International Conference on Digital Libraries, pp. 160\u2013168. ACM (1996)","DOI":"10.1145\/226931.226961"},{"key":"11_CR28","unstructured":"Teodosiu, D., Bjorner, N., Gurevich, Y., Manasse, M., Porkka, J.: Optimizing file replication over limited bandwidth networks using remote differential compression. Microsoft Research TR-2006-157 (2006)"},{"key":"11_CR29","unstructured":"Xia, W., Jiang, H., Feng, D., Hua, Y.: Silo: A similarity-locality based near-exact deduplication scheme with low ram overhead and high throughput. In: Proceedings of the 2011 USENIX Conference on USENIX Annual Technical Conference, pp. 26\u201328. USENIX Association (2011)"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-11194-0_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T04:36:41Z","timestamp":1746333401000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-11194-0_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319111933","9783319111940"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-11194-0_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2014]]}}}