{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T16:08:56Z","timestamp":1725552536891},"publisher-location":"Berlin, Heidelberg","reference-count":17,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540311423"},{"type":"electronic","value":"9783540324379"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/11610113_4","type":"book-chapter","created":{"date-parts":[[2005,12,14]],"date-time":"2005-12-14T10:23:32Z","timestamp":1134555812000},"page":"26-39","source":"Crossref","is-referenced-by-count":4,"title":["The Case of the Duplicate Documents Measurement, Search, and Science"],"prefix":"10.1007","author":[{"given":"Justin","family":"Zobel","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaniv","family":"Bernstein","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"4_CR1","first-page":"433","volume-title":"Proc. ACM-SIGIR Ann. Int. Conf. on Research and Development in Information Retrieval","author":"J. Allan","year":"2005","unstructured":"Allan, J., Carterette, B., Lewis, J.: When will information retrieval be \u201cgood enough\u201d? In: Proc. ACM-SIGIR Ann. Int. Conf. on Research and Development in Information Retrieval, pp. 433\u2013440. ACM Press, New York (2005)"},{"key":"4_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1007\/11575832_11","volume-title":"String Processing and Information Retrieval","author":"N. Askitis","year":"2005","unstructured":"Askitis, N., Zobel, J.: Cache-conscious collision resolution in string hash tables. In: Consens, M.P., Navarro, G. (eds.) SPIRE 2005. LNCS, vol.\u00a03772, pp. 91\u2013102. Springer, Heidelberg (2005)"},{"key":"4_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1007\/978-3-540-30213-1_6","volume-title":"String Processing and Information Retrieval","author":"Y. Bernstein","year":"2004","unstructured":"Bernstein, Y., Zobel, J.: A scalable system for identifying co-derivative documents. In: Apostolico, A., Melucci, M. (eds.) SPIRE 2004. LNCS, vol.\u00a03246, pp. 55\u201367. Springer, Heidelberg (2004)"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Bernstein, Y., Zobel, J.: Redundant documents and search effectiveness. In: Proc. ACM Ann. Int. Conf. on Information and Knowledge Management (CIKM) (2005) (to appear)","DOI":"10.1145\/1099554.1099733"},{"key":"4_CR5","volume-title":"The Craft of Research","author":"W.C. Booth","year":"1995","unstructured":"Booth, W.C., Colomb, G.G., Williams, J.M.: The Craft of Research. U. Chicago Press, Chicago (1995)"},{"key":"4_CR6","first-page":"398","volume-title":"Proc. ACM-SIGMOD Ann. Int. Conf. on Management of Data","author":"S. Brin","year":"1995","unstructured":"Brin, S., Davis, J., Garc\u00eda-Molina, H.: Copy detection mechanisms for digital documents. In: Carey, M., Schneider, D. (eds.) Proc. ACM-SIGMOD Ann. Int. Conf. on Management of Data, pp. 398\u2013409. ACM Press, San Jose (1995)"},{"key":"4_CR7","first-page":"21","volume-title":"Compression and Complexity of Sequences (SEQUENCES 1997)","author":"A.Z. Broder","year":"1997","unstructured":"Broder, A.Z.: On the resemblance and containment of documents. In: Compression and Complexity of Sequences (SEQUENCES 1997), pp. 21\u201329. IEEE Computer Society Press, Positano (1997)"},{"issue":"2","key":"4_CR8","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1145\/506309.506311","volume":"20","author":"A. Chowdhury","year":"2002","unstructured":"Chowdhury, A., Frieder, O., Grossman, D., McCabe, M.C.: Collection statistics for fast duplicate document detection. ACM Transactions on Information Systems (TOIS)\u00a020(2), 171\u2013191 (2002)","journal-title":"ACM Transactions on Information Systems (TOIS)"},{"key":"4_CR9","first-page":"37","volume-title":"Proc. 1st Latin AmericanWeb Congress","author":"D. Fetterly","year":"2003","unstructured":"Fetterly, D., Manasse, M., Najork, M.: On the evolution of clusters of near-duplicate web pages. In: Baeza-Yates, R. (ed.) Proc. 1st Latin AmericanWeb Congress, pp. 37\u201345. IEEE, Santiago (2003)"},{"key":"4_CR10","unstructured":"Heintze, N.: Scalable document fingerprinting. In: 1996 USENIXWorkshop on Electronic Commerce, Oakland, California, USA, pp. 191\u2013200 (1996)"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Johnson, D.S.: A theoretician\u2019s guide to the experimental analysis of algorithms. In: Goldwasser, M., Johnson, D.S., McGeoch, C.C. (eds.) Proceedings of the 5th and 6th DIMACS Implementation Challenges. American Mathematical Society, Providence (2002)","DOI":"10.1090\/dimacs\/059\/11"},{"key":"4_CR12","unstructured":"Manber, U.: Finding similar files in a large file system. In: Proc. USENIX Winter 1994 Technical Conference, San Fransisco, CA, USA, pp. 1\u201310 (1994)"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Metzler, D., Bernstein, Y., Croft, W.B., Moffat, A., Zobel, J.: Similarity measures for tracking information flow. In: Proc. ACM Ann. Int. Conf. on Information and Knowledge Management (CIKM) (2005) (to appear)","DOI":"10.1145\/1099554.1099695"},{"key":"4_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-540-30480-7_1","volume-title":"Web Information Systems \u2013 WISE 2004","author":"A. Moffat","year":"2004","unstructured":"Moffat, A., Zobel, J.: What does it mean to \u2018measure performance\u2019? In: Zhou, X., Su, S., Papazoglou, M.P., Orlowska, M.E., Jeffery, K. (eds.) WISE 2004. LNCS, vol.\u00a03306, pp. 1\u201312. Springer, Heidelberg (2004)"},{"key":"4_CR15","volume-title":"Measurement Theory","author":"F.S. Roberts","year":"1979","unstructured":"Roberts, F.S.: Measurement Theory. Addison-Wesley, Reading (1979)"},{"key":"4_CR16","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1146\/annurev.ps.45.020194.002505","volume":"45","author":"P. Suppes","year":"1994","unstructured":"Suppes, P., Pavel, M., Falmagne, J.-C.: Representations and models in psychology. Annual Review of Psychology\u00a045, 517\u2013544 (1994)","journal-title":"Annual Review of Psychology"},{"issue":"5","key":"4_CR17","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1109\/2.675631","volume":"31","author":"W.F. Tichy","year":"1998","unstructured":"Tichy, W.F.: Should computer scientists experiment more? IEEE Computer\u00a031(5), 32\u201340 (1998)","journal-title":"IEEE Computer"}],"container-title":["Lecture Notes in Computer Science","Frontiers of WWW Research and Development - APWeb 2006"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11610113_4.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T07:07:37Z","timestamp":1619507257000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11610113_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540311423","9783540324379"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/11610113_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2006]]}}}