{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:35:31Z","timestamp":1750307731375,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":18,"publisher":"ACM","license":[{"start":{"date-parts":[[2009,6,28]],"date-time":"2009-06-28T00:00:00Z","timestamp":1246147200000},"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":[[2009,6,28]]},"DOI":"10.1145\/1557019.1557137","type":"proceedings-article","created":{"date-parts":[[2009,6,30]],"date-time":"2009-06-30T13:10:54Z","timestamp":1246367454000},"page":"1087-1096","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Applying syntactic similarity algorithms for enterprise information management"],"prefix":"10.1145","author":[{"given":"Ludmila","family":"Cherkasova","sequence":"first","affiliation":[{"name":"Hewlett-Packard Labs, Palo Alto, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kave","family":"Eshghi","sequence":"additional","affiliation":[{"name":"Hewlett-Packard Labs, Palo Alto, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Charles B.","family":"Morrey","sequence":"additional","affiliation":[{"name":"Hewlett-Packard Labs, Palo Alto, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joseph","family":"Tucek","sequence":"additional","affiliation":[{"name":"Hewlett-Packard Labs, Palo Alto, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alistair","family":"Veitch","sequence":"additional","affiliation":[{"name":"Hewlett-Packard Labs, Palo Alto, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2009,6,28]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/223784.223855"},{"key":"e_1_3_2_2_2_1","volume-title":"Proc. of IEEE Conf. on the Compression and Complexity of Sequences","author":"Broder A.","year":"1997","unstructured":"A. Broder . On the Resemblance and Containment of Documents . Proc. of IEEE Conf. on the Compression and Complexity of Sequences , June , 1997 . A. Broder. On the Resemblance and Containment of Documents. Proc. of IEEE Conf. on the Compression and Complexity of Sequences, June, 1997."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/276698.276781"},{"key":"e_1_3_2_2_4_1","volume-title":"Conference on World Wide Web","author":"Broder A.","year":"1997","unstructured":"A. Broder , S. Glassman , M. Manasse , G. Zweig . Syntactic clustering of the Web. Selected papers from the 6-th Intl . Conference on World Wide Web , Sept. 1997 , Santa Clara, CA, USA. A. Broder, S. Glassman, M. Manasse, G. Zweig. Syntactic clustering of the Web. Selected papers from the 6-th Intl. Conference on World Wide Web, Sept. 1997, Santa Clara, CA, USA."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/509907.509965"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/506309.506311"},{"key":"e_1_3_2_2_7_1","volume-title":"On the Evolution of Clusters of Near-Duplicate Web Pages. Journal of Web Engineering","author":"Fetterly D.","year":"2004","unstructured":"D. Fetterly , M. Manasse , M. Najork . On the Evolution of Clusters of Near-Duplicate Web Pages. Journal of Web Engineering , vol. 2 , N. 4, Oct , 2004 . D. Fetterly, M. Manasse, M. Najork. On the Evolution of Clusters of Near-Duplicate Web Pages. Journal of Web Engineering, vol.2, N.4, Oct, 2004."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1076034.1076066"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1081870.1081916"},{"key":"e_1_3_2_2_10_1","volume-title":"Proc. of the Second USENIX Workshop on Electronic Commerce","author":"Heintze N.","year":"1996","unstructured":"N. Heintze . Scalable document fingerprinting . Proc. of the Second USENIX Workshop on Electronic Commerce , 1996 . N. Heintze. Scalable document fingerprinting. Proc. of the Second USENIX Workshop on Electronic Commerce, 1996."},{"key":"e_1_3_2_2_11_1","volume-title":"Lihue","author":"Henson V.","year":"2003","unstructured":"V. Henson . An analysis of compare-by-hash.Proc. of the 9th conference on Hot Topics in Operating Systems (HotOS'03) , Lihue , Hawaii, USA , 2003 . V. Henson. An analysis of compare-by-hash.Proc. of the 9th conference on Hot Topics in Operating Systems (HotOS'03), Lihue, Hawaii, USA, 2003."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148222"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1002\/asi.10170"},{"key":"e_1_3_2_2_14_1","unstructured":"B. Jenkins. Hash Functions. \"Algorithm Alley\" Dr. Dobb's Journal September 1997 http:\/\/www.ddj.com\/184410284  B. Jenkins. Hash Functions. \"Algorithm Alley\" Dr. Dobb's Journal September 1997 http:\/\/www.ddj.com\/184410284"},{"key":"e_1_3_2_2_15_1","volume-title":"Proc. of the","author":"Manber U.","year":"1994","unstructured":"U. Manber . Finding similar files in a large file system . Proc. of the Winter 1994 USENIX Conference , 1994. U. Manber. Finding similar files in a large file system. Proc. of the Winter 1994 USENIX Conference, 1994."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/502034.502052"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/226931.226961"},{"key":"e_1_3_2_2_19_1","volume-title":"Proc. of Workshop on Web Databases (WebDB'96)","author":"Shivakumar N.","year":"1996","unstructured":"N. Shivakumar and H. Garcia-Molina . Finding near-replicas of documents on the web . Proc. of Workshop on Web Databases (WebDB'96) , Valencia, Spain , 1996 . N. Shivakumar and H. Garcia-Molina. Finding near-replicas of documents on the web. Proc. of Workshop on Web Databases (WebDB'96), Valencia, Spain, 1996."}],"event":{"name":"KDD09: The 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","ACM Association for Computing Machinery"],"location":"Paris France","acronym":"KDD09"},"container-title":["Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1557019.1557137","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1557019.1557137","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T13:38:42Z","timestamp":1750253922000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1557019.1557137"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,6,28]]},"references-count":18,"alternative-id":["10.1145\/1557019.1557137","10.1145\/1557019"],"URL":"https:\/\/doi.org\/10.1145\/1557019.1557137","relation":{},"subject":[],"published":{"date-parts":[[2009,6,28]]},"assertion":[{"value":"2009-06-28","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}