{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T13:32:56Z","timestamp":1760707976774,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":18,"publisher":"ACM","license":[{"start":{"date-parts":[[2007,7,23]],"date-time":"2007-07-23T00:00:00Z","timestamp":1185148800000},"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":[[2007,7,23]]},"DOI":"10.1145\/1277741.1277782","type":"proceedings-article","created":{"date-parts":[[2008,9,18]],"date-time":"2008-09-18T11:59:52Z","timestamp":1221739192000},"page":"223-230","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Multiple-signal duplicate detection for search evaluation"],"prefix":"10.1145","author":[{"given":"Scott","family":"Huffman","sequence":"first","affiliation":[{"name":"Google Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"April","family":"Lehman","sequence":"additional","affiliation":[{"name":"Google Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexei","family":"Stolboushkin","sequence":"additional","affiliation":[{"name":"Google Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Howard","family":"Wong-Toi","sequence":"additional","affiliation":[{"name":"Google Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fan","family":"Yang","sequence":"additional","affiliation":[{"name":"Google Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hein","family":"Roehrig","sequence":"additional","affiliation":[{"name":"Google Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2007,7,23]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/223784.223855"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0169-7552(97)00031-7"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/509907.509965"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2005.844059"},{"key":"e_1_3_2_1_5_1","first-page":"115","volume-title":"Proc. of the 12th International Conference on Machine Learning","author":"Cohen W. W.","year":"1995","unstructured":"W. W. Cohen . Fast effective rule induction. In A. Prieditis and S. Russell, editors , Proc. of the 12th International Conference on Machine Learning , pages 115 -- 123 , Tahoe City, CA , July 9-12, 1995 . Morgan Kaufmann. W. W. Cohen. Fast effective rule induction. In A. Prieditis and S. Russell, editors, Proc. of the 12th International Conference on Machine Learning, pages 115--123, Tahoe City, CA, July 9-12, 1995. Morgan Kaufmann."},{"key":"e_1_3_2_1_6_1","unstructured":"Crowbar. http:\/\/simile.mit.edu\/wiki\/Crowbar.  Crowbar. http:\/\/simile.mit.edu\/wiki\/Crowbar."},{"key":"e_1_3_2_1_7_1","volume-title":"Detecting query-specific duplicate documents","author":"Gomes B.","year":"2003","unstructured":"B. Gomes and B. Smith . Detecting query-specific duplicate documents , 2003 . U.S. Patent 6,615,209. B. Gomes and B. Smith. Detecting query-specific duplicate documents, 2003. U.S. Patent 6,615,209."},{"key":"e_1_3_2_1_8_1","volume-title":"USENIX Workshop on Electronic Commerce","author":"Heintze N.","year":"1996","unstructured":"N. Heintze . Scalable document fingerprinting . In USENIX Workshop on Electronic Commerce , 1996 . N. Heintze. Scalable document fingerprinting. In USENIX Workshop on Electronic Commerce, 1996."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148222"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/582415.582418"},{"key":"e_1_3_2_1_11_1","first-page":"1","volume-title":"USENIX Winter","author":"Manber U.","year":"1994","unstructured":"U. Manber . Finding similar files in a large file system . In USENIX Winter , pages 1 -- 10 , 1994 . U. Manber. Finding similar files in a large file system. In USENIX Winter, pages 1--10, 1994."},{"key":"e_1_3_2_1_12_1","unstructured":"Open directory project. http:\/\/www.dmoz.org.  Open directory project. http:\/\/www.dmoz.org."},{"key":"e_1_3_2_1_13_1","volume-title":"Morgan Kaufmann","author":"Quinlan J. R.","year":"1993","unstructured":"J. R. Quinlan . C4.5 : Programs for Machine Learning . Morgan Kaufmann , 1993 . J. R. Quinlan. C4.5: Programs for Machine Learning. Morgan Kaufmann, 1993."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/872757.872770"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/223784.223855"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/226931.226961"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/646543.696353"},{"key":"e_1_3_2_1_18_1","volume-title":"Morgan-Kaufmann","author":"Witten I. H.","year":"1999","unstructured":"I. H. Witten and E. Frank . Weka: Practical machine learning tools and techniques with Java implementations . Morgan-Kaufmann , 1999 . I. H. Witten and E. Frank. Weka: Practical machine learning tools and techniques with Java implementations. Morgan-Kaufmann, 1999."}],"event":{"name":"SIGIR07: The 30th Annual International SIGIR Conference","sponsor":["ACM Association for Computing Machinery","SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Amsterdam The Netherlands","acronym":"SIGIR07"},"container-title":["Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1277741.1277782","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1277741.1277782","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T14:58:14Z","timestamp":1750258694000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1277741.1277782"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007,7,23]]},"references-count":18,"alternative-id":["10.1145\/1277741.1277782","10.1145\/1277741"],"URL":"https:\/\/doi.org\/10.1145\/1277741.1277782","relation":{},"subject":[],"published":{"date-parts":[[2007,7,23]]},"assertion":[{"value":"2007-07-23","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}