{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T12:14:58Z","timestamp":1763468098312},"publisher-location":"Berlin, Heidelberg","reference-count":26,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642332890"},{"type":"electronic","value":"9783642332906"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-33290-6_22","type":"book-chapter","created":{"date-parts":[[2012,9,20]],"date-time":"2012-09-20T10:16:01Z","timestamp":1348136161000},"page":"197-208","source":"Crossref","is-referenced-by-count":13,"title":["Identifying \u201cSoft 404\u201d Error Pages: Analyzing the Lexical Signatures of Documents in Distributed Collections"],"prefix":"10.1007","author":[{"given":"Luis","family":"Meneses","sequence":"first","affiliation":[]},{"given":"Richard","family":"Furuta","sequence":"additional","affiliation":[]},{"given":"Frank","family":"Shipman","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"22_CR1","unstructured":"Bush, V.: As we may think. The Atlantic (1945), \n                    \n                      http:\/\/www.theatlantic.com\/magazine\/archive\/1945\/07\/as-we-may-think\/3881\/"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Logasa Bogen, P., Pogue, D., Poursardar, F., Li, Y., Furuta, R., Shipman, F.: WPv4: a re-imagined Walden\u2019s paths to support diverse user communities. Presented at the Proceeding of the 11th Annual International ACM\/IEEE Joint Conference on Digital Libraries, Ottawa, Ontario, Canada (2011)","DOI":"10.1145\/1998076.1998164"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Shipman, F., Hsieh, H., Maloor, P., Moore, J.M.: The visual knowledge builder: a second generation spatial hypertext. Proceedings of the twelfth ACM conference on Hypertext and Hypermedia - HYPERTEXT 2001, Arhus, Denmark, pp. 113\u2013122 (2001)","DOI":"10.1145\/504243.504245"},{"key":"22_CR4","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1145\/1592761.1592794","volume":"52","author":"F. McCown","year":"2009","unstructured":"McCown, F., Marshall, C.C., Nelson, M.L.: Why web sites are lost (and how they\u2019re sometimes found). Commun. ACM\u00a052, 141\u2013145 (2009)","journal-title":"Commun. ACM"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Francisco-Revilla, L., Shipman, F., Furuta, R., Karadkar, U., Arora, A.: Managing change on the web. Presented at the Proceedings of the 1st ACM\/IEEE-CS Joint Conference on Digital Libraries, Roanoke, Virginia, United States (2001)","DOI":"10.1145\/379437.379973"},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Francisco-Revilla, L., Shipman, F., Furuta, R., Karadkar, U., Arora, A.: Perception of content, structure, and presentation changes in Web-based hypertext. Presented at the Proceedings of the 12th ACM Conference on Hypertext and Hypermedia, Arhus, Denmark (2001)","DOI":"10.1145\/504264.504266"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Logasa Bogen, P., Francisco-Revilla, L., Furuta, R., Hubbard, T., Karadkar, U.P., Shipman, F.: Longitudinal study of changes in blogs. Presented at the Proceedings of the 7th ACM\/IEEE-CS Joint Conference on Digital Libraries, Vancouver, BC, Canada (2007)","DOI":"10.1145\/1255175.1255201"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Klein, M., Shipman, J., Nelson, M.L.: Is this a good title? Presented at the Proceedings of the 21st ACM Conference on Hypertext and Hypermedia, Toronto, Ontario, Canada (2010)","DOI":"10.1145\/1810617.1810621"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Klein, M., Nelson, M.L.: Evaluating methods to rediscover missing web pages from the web infrastructure. Presented at the Proceedings of the 10th Annual Joint Conference on Digital Libraries, Gold Coast, Queensland, Australia (2010)","DOI":"10.1145\/1816123.1816133"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Harrison, T.L., Nelson, M.L.: Just-in-time recovery of missing web pages. Presented at the Proceedings of the Seventeenth Conference on Hypertext and Hypermedia, Odense, Denmark (2006)","DOI":"10.1145\/1149941.1149971"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Klein, M., Ware, J., Nelson, M.L.: Rediscovering missing web pages using link neighborhood lexical signatures. Presented at the Proceedings of the 11th Annual International ACM\/IEEE Joint Conference on Digital Libraries, Ottawa, Ontario, Canada (2011)","DOI":"10.1145\/1998076.1998101"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Dalal, Z., Dash, S., Dave, P., Francisco-Revilla, L., Furuta, R., Karadkar, U., Shipman, F.: Managing distributed collections: evaluating web page changes, movement, and replacement. Presented at the Proceedings of the 4th ACM\/IEEE-CS Joint Conference on Digital Libraries, Tuscon, AZ, USA (2004)","DOI":"10.1145\/996350.996387"},{"key":"22_CR13","unstructured":"Johnson, D.B.: Enabling the reuse of World Wide Web documents in tutorials. University of Washington (1997)"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Park, S.-T., Pennock, D.M., Giles, C.L., Krovetz, R.: Analysis of lexical signatures for finding lost or related documents. Presented at the Proceedings of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, Tampere, Finland (2002)","DOI":"10.1145\/564376.564381"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Baeza-Yates, R., Pereira, I., Ziviani, N.: Genealogical trees on the web: a search engine user perspective. Presented at the Proceedings of the 17th International Conference on World Wide Web, Beijing, China (2008)","DOI":"10.1145\/1367497.1367548"},{"key":"22_CR16","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1145\/367701.367702","volume":"32","author":"H. Ashman","year":"2000","unstructured":"Ashman, H.: Electronic document addressing: dealing with change. ACM Comput. Surv.\u00a032, 201\u2013212 (2000)","journal-title":"ACM Comput. Surv."},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Ashman, H., Davis, H., Whitehead, J., Caughey, S.: Missing the 404: link integrity on the World Wide Web. Presented at the Proceedings of the Seventh International Conference on World Wide Web 7, Brisbane, Australia (1998)","DOI":"10.1016\/S0169-7552(98)00131-7"},{"key":"22_CR18","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1145\/345966.346026","volume":"31","author":"H.C. Davis","year":"1999","unstructured":"Davis, H.C.: Hypertext link integrity. ACM Comput. Surv.\u00a031, 28 (1999)","journal-title":"ACM Comput. Surv."},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Davis, H.C.: Referential integrity of links in open hypermedia systems. Presented at the Proceedings of the Ninth ACM Conference on Hypertext and Hypermedia: Links, Objects, Pittsburgh, Pennsylvania, United States (1998)","DOI":"10.1145\/276627.276650"},{"key":"22_CR20","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1038\/scientificamerican0397-82","volume":"276","author":"B. Kahle","year":"1997","unstructured":"Kahle, B.: Preserving the Internet. Scientific American\u00a0276, 82\u201383 (1997)","journal-title":"Scientific American"},{"key":"22_CR21","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1002\/asi.10018","volume":"53","author":"W. Koehler","year":"2002","unstructured":"Koehler, W.: Web page change and persistence\u2014a four-year longitudinal study. J. Am. Soc. Inf. Sci. Technol.\u00a053, 162\u2013171 (2002)","journal-title":"J. Am. Soc. Inf. Sci. Technol."},{"key":"22_CR22","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1145\/602421.602422","volume":"46","author":"D. Spinellis","year":"2003","unstructured":"Spinellis, D.: The decay and failures of web references. Commun. ACM\u00a046, 71\u201377 (2003)","journal-title":"Commun. ACM"},{"key":"22_CR23","unstructured":"Phelps, T.A., Wilensky, R.: Robust Hyperlinks Cost Just Five Words Each. University of California at Berkeley (2000)"},{"key":"22_CR24","doi-asserted-by":"publisher","first-page":"540","DOI":"10.1145\/1028099.1028101","volume":"22","author":"S.-T. Park","year":"2004","unstructured":"Park, S.-T., Pennock, D.M., Giles, C.L., Krovetz, R.: Analysis of lexical signatures for improving information persistence on the World Wide Web. ACM Trans. Inf. Syst.\u00a022, 540\u2013572 (2004)","journal-title":"ACM Trans. Inf. Syst."},{"key":"22_CR25","doi-asserted-by":"crossref","unstructured":"Bar-Yossef, Z., Broder, A.Z., Kumar, R., Tomkins, A.: Sic transit gloria telae: towards an understanding of the web\u2019s decay. Presented at the Proceedings of the 13th International Conference on World Wide Web, New York, NY, USA (2004)","DOI":"10.1145\/988672.988716"},{"key":"22_CR26","doi-asserted-by":"crossref","unstructured":"Jatowt, A.: Web page summarization using dynamic content. Presented at the Proceedings of the 13th International World Wide Web Conference on Alternate Track Papers and Posters, New York, NY, USA (2004)","DOI":"10.1145\/1013367.1013467"}],"container-title":["Lecture Notes in Computer Science","Theory and Practice of Digital Libraries"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-33290-6_22.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T12:02:59Z","timestamp":1620129779000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-33290-6_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642332890","9783642332906"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-33290-6_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}