{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:21:10Z","timestamp":1750306870552,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":9,"publisher":"ACM","license":[{"start":{"date-parts":[[2013,12,5]],"date-time":"2013-12-05T00:00:00Z","timestamp":1386201600000},"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":[[2013,12,5]]},"DOI":"10.1145\/2537734.2537746","type":"proceedings-article","created":{"date-parts":[[2013,12,10]],"date-time":"2013-12-10T13:28:27Z","timestamp":1386682107000},"page":"101-104","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Malformed UTF-8 and spam"],"prefix":"10.1145","author":[{"given":"Matt","family":"Crane","sequence":"first","affiliation":[{"name":"University of Otago, Dunedin, New Zealand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Trotman","sequence":"additional","affiliation":[{"name":"University of Otago, Dunedin, New Zealand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Richard","family":"O'Keefe","sequence":"additional","affiliation":[{"name":"University of Otago, Dunedin, New Zealand"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2013,12,5]]},"reference":[{"volume-title":"http:\/\/boston.lti.cs.cmu.edu\/clueweb09\/wiki\/tiki-index.php?page=Page+Encodings accessed","year":"2013","key":"e_1_3_2_1_1_1","unstructured":"ClueWeb09 Wiki. http:\/\/boston.lti.cs.cmu.edu\/clueweb09\/wiki\/tiki-index.php?page=Page+Encodings accessed 3 Oct 2013 . ClueWeb09 Wiki. http:\/\/boston.lti.cs.cmu.edu\/clueweb09\/wiki\/tiki-index.php?page=Page+Encodings accessed 3 Oct 2013."},{"volume-title":"http:\/\/docs.oracle.com\/javase\/6\/docs\/api\/java\/io\/DataInput.html#modified-utf-8 accessed","year":"2013","key":"e_1_3_2_1_2_1","unstructured":"Modified UTF-8. http:\/\/docs.oracle.com\/javase\/6\/docs\/api\/java\/io\/DataInput.html#modified-utf-8 accessed 3 Oct 2013 . Modified UTF-8. http:\/\/docs.oracle.com\/javase\/6\/docs\/api\/java\/io\/DataInput.html#modified-utf-8 accessed 3 Oct 2013."},{"volume-title":"http:\/\/www.unicode.org\/versions\/Unicode6.0.0\/accessed","year":"2013","key":"e_1_3_2_1_3_1","unstructured":"Unicode 6.0.0. http:\/\/www.unicode.org\/versions\/Unicode6.0.0\/accessed 3 Oct 2013 . Unicode 6.0.0. http:\/\/www.unicode.org\/versions\/Unicode6.0.0\/accessed 3 Oct 2013."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10791-011-9162-z"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2407085.2407086"},{"key":"e_1_3_2_1_6_1","unstructured":"M. Davis. Moving to Unicode 5.1. http:\/\/googleblog.blogspot.com\/2008\/05\/moving-to-unicode-51.html.  M. Davis. Moving to Unicode 5.1. http:\/\/googleblog.blogspot.com\/2008\/05\/moving-to-unicode-51.html."},{"key":"e_1_3_2_1_7_1","volume-title":"Unicode technical report 36: Unicode security considerations. Technical report","author":"Davis M.","year":"2012","unstructured":"M. Davis and M. Suignard . Unicode technical report 36: Unicode security considerations. Technical report , 2012 . M. Davis and M. Suignard. Unicode technical report 36: Unicode security considerations. Technical report, 2012."},{"key":"e_1_3_2_1_8_1","first-page":"40","volume-title":"Proceedings of the SIGIR 2012 Workshop on Open Source Information Retrieval","author":"Trotman A.","year":"2012","unstructured":"A. Trotman , X. Jia , and M. Crane . Towards an efficient and effective search engine . In Proceedings of the SIGIR 2012 Workshop on Open Source Information Retrieval , pages 40 -- 47 , 2012 . A. Trotman, X. Jia, and M. Crane. Towards an efficient and effective search engine. In Proceedings of the SIGIR 2012 Workshop on Open Source Information Retrieval, pages 40--47, 2012."},{"key":"e_1_3_2_1_9_1","volume-title":"Nov.","author":"Yergeau F.","year":"2003","unstructured":"F. Yergeau . UTF-8 , a transformation format of ISO 10646. RFC 3629 (INTERNET STANDARD) , Nov. 2003 . F. Yergeau. UTF-8, a transformation format of ISO 10646. RFC 3629 (INTERNET STANDARD), Nov. 2003."}],"event":{"name":"ADCS '13: The Australasian Document Computing Symposium","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Brisbane Queensland Australia","acronym":"ADCS '13"},"container-title":["Proceedings of the 18th Australasian Document Computing Symposium"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2537734.2537746","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2537734.2537746","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T08:18:13Z","timestamp":1750234693000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2537734.2537746"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,12,5]]},"references-count":9,"alternative-id":["10.1145\/2537734.2537746","10.1145\/2537734"],"URL":"https:\/\/doi.org\/10.1145\/2537734.2537746","relation":{},"subject":[],"published":{"date-parts":[[2013,12,5]]},"assertion":[{"value":"2013-12-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}