{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T06:05:43Z","timestamp":1775282743788,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2005,10,31]],"date-time":"2005-10-31T00:00:00Z","timestamp":1130716800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2005,10,31]]},"DOI":"10.1145\/1099554.1099733","type":"proceedings-article","created":{"date-parts":[[2006,2,6]],"date-time":"2006-02-06T15:52:40Z","timestamp":1139241160000},"page":"736-743","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":31,"title":["Redundant documents and search effectiveness"],"prefix":"10.1145","author":[{"given":"Yaniv","family":"Bernstein","sequence":"first","affiliation":[{"name":"RMIT University, Melbourne, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Justin","family":"Zobel","sequence":"additional","affiliation":[{"name":"RMIT University, Melbourne, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2005,10,31]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/860435.860493"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30213-1_6"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/223784.223855"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0169-7552(97)00031-7"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/345508.345543"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/342009.335429"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/506309.506311"},{"key":"e_1_3_2_1_8_1","volume-title":"Overview of the TREC 2004 Terabyte Track, in 'Proceedings of the 13th Text REtrieval Conference (TREC 2004)","author":"Clarke C.","year":"2004","unstructured":"Clarke , C. , Craswell , N. & Soboroff , I. ( 2004 ), Overview of the TREC 2004 Terabyte Track, in 'Proceedings of the 13th Text REtrieval Conference (TREC 2004) '.]] Clarke, C., Craswell, N. & Soboroff, I. (2004), Overview of the TREC 2004 Terabyte Track, in 'Proceedings of the 13th Text REtrieval Conference (TREC 2004)'.]]"},{"key":"e_1_3_2_1_9_1","first-page":"37","volume-title":"IEEE","author":"Fetterly D.","year":"2003","unstructured":"Fetterly , D. , Manasse , M. & Najork , M. ( 2003 ), On the Evolution of Clusters of Near-Duplicate Web Pages, in 'Proceedings of the 1st Latin American Web Congress ', IEEE , pp. 37 -- 45 .]] Fetterly, D., Manasse, M. & Najork, M. (2003), On the Evolution of Clusters of Near-Duplicate Web Pages, in 'Proceedings of the 1st Latin American Web Congress', IEEE, pp. 37--45.]]"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/979922.979924"},{"key":"e_1_3_2_1_11_1","volume-title":"Overview of the TREC 2002 Novelty Track, in 'The Eleventh Text REtrieval Conference (TREC 2002)","author":"Harman D.","year":"2002","unstructured":"Harman , D. ( 2002 ), Overview of the TREC 2002 Novelty Track, in 'The Eleventh Text REtrieval Conference (TREC 2002) '.]] Harman, D. (2002), Overview of the TREC 2002 Novelty Track, in 'The Eleventh Text REtrieval Conference (TREC 2002)'.]]"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/243199.243216"},{"key":"e_1_3_2_1_13_1","volume-title":"'1996 USENIX Workshop on Electronic Commerce'.]]","author":"Heintze N.","year":"1996","unstructured":"Heintze , N. ( 1996 ), Scalable Document Fingerprinting , in '1996 USENIX Workshop on Electronic Commerce'.]] Heintze, N. (1996), Scalable Document Fingerprinting, in '1996 USENIX Workshop on Electronic Commerce'.]]"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1002\/asi.10170"},{"key":"e_1_3_2_1_15_1","first-page":"1","volume-title":"Finding Similar Files in a Large File System, in 'Proceedings of the USENIX","author":"Manber U.","year":"1994","unstructured":"Manber , U. ( 1994 ), Finding Similar Files in a Large File System, in 'Proceedings of the USENIX Winter 1994 Technical Conference ', pp. 1 -- 10 .]] Manber, U. (1994), Finding Similar Files in a Large File System, in 'Proceedings of the USENIX Winter 1994 Technical Conference', pp. 1--10.]]"},{"key":"e_1_3_2_1_16_1","volume-title":"The MD5 Message-Digest Algorithm'. RFC 1321.]]","author":"Rivest R.","year":"1992","unstructured":"Rivest , R. ( 1992 ), ' The MD5 Message-Digest Algorithm'. RFC 1321.]] Rivest, R. (1992), 'The MD5 Message-Digest Algorithm'. RFC 1321.]]"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/1076034.1076064"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/872757.872770"},{"key":"e_1_3_2_1_19_1","volume-title":"SCAM: A Copy Detection Mechanism for Digital Documents, in 'Proceedings of the Second Annual Conference on the Theory and Practice of Digital Libraries'.]]","author":"Shivakumar N.","year":"1995","unstructured":"Shivakumar , N. & Garc\u00ed\u00eda-Molina , H. ( 1995 ), SCAM: A Copy Detection Mechanism for Digital Documents, in 'Proceedings of the Second Annual Conference on the Theory and Practice of Digital Libraries'.]] Shivakumar, N. & Garc\u00ed\u00eda-Molina, H. (1995), SCAM: A Copy Detection Mechanism for Digital Documents, in 'Proceedings of the Second Annual Conference on the Theory and Practice of Digital Libraries'.]]"},{"key":"e_1_3_2_1_20_1","volume-title":"WebDB","author":"Shivakumar N.","year":"1999","unstructured":"Shivakumar , N. & Garc\u00ed\u00eda-Molina , H. ( 1999 ), Finding Near-Replicas of Documents on the Web, in 'WEBDB: International Workshop on the World Wide Web and Databases , WebDB ', Springer-Verlag .]] Shivakumar, N. & Garc\u00ed\u00eda-Molina, H. (1999), Finding Near-Replicas of Documents on the Web, in 'WEBDB: International Workshop on the World Wide Web and Databases, WebDB', Springer-Verlag.]]"},{"key":"e_1_3_2_1_21_1","first-page":"38","volume-title":"Overview of the TREC 2003 Novelty Track, in 'The Twelfth Text REtrieval Conference (TREC 2003)","author":"Soboroff I.","year":"2003","unstructured":"Soboroff , I. & Harman , D. ( 2003 ), Overview of the TREC 2003 Novelty Track, in 'The Twelfth Text REtrieval Conference (TREC 2003) ', pp. 38 -- 53 .]] Soboroff, I. & Harman, D. (2003), Overview of the TREC 2003 Novelty Track, in 'The Twelfth Text REtrieval Conference (TREC 2003)', pp. 38--53.]]"},{"key":"e_1_3_2_1_22_1","volume-title":"Butterworth-Heinemann.]]","author":"van Rijsbergen C. J.","year":"1979","unstructured":"van Rijsbergen , C. J. ( 1979 ), Information Retrieval , Butterworth-Heinemann.]] van Rijsbergen, C. J. (1979), Information Retrieval, Butterworth-Heinemann.]]"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/564376.564432"},{"key":"e_1_3_2_1_24_1","volume-title":"Morgan Kauffman.]]","author":"Witten I. H.","year":"1999","unstructured":"Witten , I. H. , Moffat , A. & Bell , T. C. ( 1999 ), Managing Gigabytes: Compressing and Indexing Documents and Images , Morgan Kauffman.]] Witten, I. H., Moffat, A. & Bell, T. C. (1999), Managing Gigabytes: Compressing and Indexing Documents and Images, Morgan Kauffman.]]"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/860435.860440"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/564376.564393"}],"event":{"name":"CIKM05: Conference on Information and Knowledge Management","location":"Bremen Germany","acronym":"CIKM05","sponsor":["ACM Association for Computing Machinery","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 14th ACM international conference on Information and knowledge management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1099554.1099733","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1099554.1099733","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T16:18:44Z","timestamp":1750263524000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1099554.1099733"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005,10,31]]},"references-count":26,"alternative-id":["10.1145\/1099554.1099733","10.1145\/1099554"],"URL":"https:\/\/doi.org\/10.1145\/1099554.1099733","relation":{},"subject":[],"published":{"date-parts":[[2005,10,31]]},"assertion":[{"value":"2005-10-31","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}