{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,15]],"date-time":"2024-09-15T14:24:23Z","timestamp":1726410263005},"publisher-location":"Berlin, Heidelberg","reference-count":15,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642324970"},{"type":"electronic","value":"9783642324987"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-32498-7_16","type":"book-chapter","created":{"date-parts":[[2012,8,14]],"date-time":"2012-08-14T10:04:28Z","timestamp":1344938668000},"page":"203-217","source":"Crossref","is-referenced-by-count":0,"title":["Near Duplicate Document Detection for Large Information Flows"],"prefix":"10.1007","author":[{"given":"Daniele","family":"Montanari","sequence":"first","affiliation":[]},{"given":"Piera Laura","family":"Puglisi","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"16_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/3-540-47555-9_6","volume-title":"Advances in Cryptology - EUROCRYPT \u201992","author":"T.A. Berson","year":"1993","unstructured":"Berson, T.A.: Differential Cryptanalysis Mod 2 with Applications to MD5. In: Rueppel, R.A. (ed.) EUROCRYPT 1992. LNCS, vol.\u00a0658, pp. 71\u201380. Springer, Heidelberg (1993)"},{"key":"16_CR2","unstructured":"Zhe, W., et al.: Clean-living: Eliminating Near-Duplicates in lifetime Personal Storage. Technical Report (September 2005)"},{"key":"16_CR3","unstructured":"Kumar, J.P., et al.: Duplicate and Near Duplicate Documents Detection: A Review. European Journal of Scientific Research (2009)"},{"key":"16_CR4","unstructured":"Udi, M.: Finding Similar Files in a Large File System. In: USENIX Winter Technical Conference, CA (January 1994)"},{"key":"16_CR5","unstructured":"Andrei, Z., et al.: Some applications of Rabin\u2019s fingerprinting method. Sequences II: Methods in Communications, Security, and Computer Science. Springer (1993)"},{"issue":"2","key":"16_CR6","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1145\/506309.506311","volume":"20","author":"A. Chowdhury","year":"2002","unstructured":"Chowdhury, A., et al.: Collection statistics for fast duplicate document detection. ACM Transaction on Information Systems\u00a020(2), 171\u2013191 (2002)","journal-title":"ACM Transaction on Information Systems"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Broder, A.Z.: Identifying and Filtering Near-Duplicate Documents. In: Proceedings of COM 2000 (2000)","DOI":"10.1007\/3-540-45123-4_1"},{"key":"16_CR8","unstructured":"Gravano, L., et al.: Approximate string joins in a database (almost) for free. In: VLDB 2001 (2001)"},{"key":"16_CR9","unstructured":"Ilinsky, et al.: An efficient method to detect duplicates of Web documents with the use of inverted index"},{"key":"16_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1007\/978-3-642-15105-7_25","volume-title":"Data Warehousing and Knowledge Discovery","author":"A. Ferro","year":"2010","unstructured":"Ferro, A., Giugno, R., Puglisi, P.L., Pulvirenti, A.: An Efficient Duplicate Record Detection Using q-Grams Array Inverted Index. In: Pedersen, T.B., Mohania, M.K., Tjoa, A.M. (eds.) DaWaK 2010. LNCS, vol.\u00a06263, pp. 309\u2013323. Springer, Heidelberg (2010)"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Theobald, et al.: SpotSigs: Robust and Efficient Near Duplicate Detection in Large Web Collections. In: Proceedings of SIGIR (2008)","DOI":"10.1145\/1390334.1390431"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Indyk, P., et al.: Approximate nearest neighbors: towards removing the curse of dimensionality. In: STOC (1998)","DOI":"10.1145\/276698.276876"},{"key":"16_CR13","unstructured":"http:\/\/en.wikipedia.org\/wiki\/Viral_marketing"},{"key":"16_CR14","unstructured":"http:\/\/en.wikipedia.org\/wiki\/SHA-1"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Kolcz, A., et al.: Improved robustness of signature-based near replica detection via lexicon randomization. In: KDD 2004 (2004)","DOI":"10.1145\/1014052.1014127"}],"container-title":["Lecture Notes in Computer Science","Multidisciplinary Research and Practice for Information Systems"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-32498-7_16.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T08:04:39Z","timestamp":1620115479000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-32498-7_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642324970","9783642324987"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-32498-7_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}