{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T15:56:08Z","timestamp":1774194968193,"version":"3.50.1"},"reference-count":78,"publisher":"Springer Science and Business Media LLC","issue":"1-2","license":[{"start":{"date-parts":[[2014,2,1]],"date-time":"2014-02-01T00:00:00Z","timestamp":1391212800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/2.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Digit Libr"],"published-print":{"date-parts":[[2014,4]]},"DOI":"10.1007\/s00799-014-0108-0","type":"journal-article","created":{"date-parts":[[2014,1,31]],"date-time":"2014-01-31T22:18:52Z","timestamp":1391206732000},"page":"17-38","source":"Crossref","is-referenced-by-count":14,"title":["Moved but not gone: an evaluation of real-time methods for discovering replacement web pages"],"prefix":"10.1007","volume":"14","author":[{"given":"Martin","family":"Klein","sequence":"first","affiliation":[]},{"given":"Michael L.","family":"Nelson","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2014,2,1]]},"reference":[{"key":"108_CR1","unstructured":"Berners-Lee, T.: Cool URIs don\u2019t change http:\/\/www.w3.org\/Provider\/Style\/URI.html (1998)"},{"key":"108_CR2","doi-asserted-by":"crossref","unstructured":"McCown, F., Marshall, C.C., Nelson, M.L.: Why websites are lost (and how they\u2019re sometimes found). Commun. ACM 52(11) (2008)","DOI":"10.1145\/1592761.1592794"},{"key":"108_CR3","unstructured":"Van de Sompel, H., Nelson, M.L., Sanderson, R., Balakireva, L., Ainsworth, S., Shankar, H.: Memento: time travel for the web. Tech. Rep. arXiv:0911.1112 (2009)"},{"key":"108_CR4","unstructured":"Klein, M.: Using the Web Infrastructure for Real Time Recovery of Missing Web Pages. Ph.D. thesis, Old Dominion University (2011)"},{"issue":"1\u20136","key":"108_CR5","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1016\/S1389-1286(00)00055-4","volume":"33","author":"MR Henzinger","year":"2000","unstructured":"Henzinger, M.R., Heydon, A., Mitzenmacher, M., Najork, M.: On near-uniform URL sampling. Comput. Netw. 33(1\u20136), 295\u2013308 (2000)","journal-title":"Comput. Netw."},{"key":"108_CR6","unstructured":"Rusmevichientong, P., Pennock, D.M., Lawrence, S., Giles, C.L.: Methods for sampling pages uniformly from the world wide web. In: AAAI Fall Symposium on Using Uncertainty Within Computation, pp. 121\u2013128 (2001)"},{"key":"108_CR7","doi-asserted-by":"crossref","unstructured":"Harth, A., Umbrich, J., Decker, S.: MultiCrawler: a pipelined architecture for crawling and indexing semantic web data. In: The Semantic Web-ISWC 2006, vol. 4273, pp. 258\u2013271 (2006)","DOI":"10.1007\/11926078_19"},{"key":"108_CR8","doi-asserted-by":"crossref","unstructured":"Noll, M.G., Meinel, C.: Exploring social annotations for web document classification. In: Proceedings of SAC \u201908, pp. 2315\u20132320 (2008)","DOI":"10.1145\/1363686.1364235"},{"key":"108_CR9","doi-asserted-by":"crossref","unstructured":"Umbrich, J., Harth, A., Hogan, A., Decker, S.: Four heuristics to guide structured content crawling. In: Proceedings of ICWE \u201908, pp. 196\u2013202 (2008)","DOI":"10.1109\/ICWE.2008.42"},{"key":"108_CR10","unstructured":"Klein, M.: The \u201cBook of the Dead\u201d Corpus. http:\/\/ws-dl.blogspot.com\/2011\/06\/201-06-17-book-of-dead-corpus.html"},{"key":"108_CR11","doi-asserted-by":"crossref","unstructured":"Ainsworth, S.G., Alsum, A., SalahEldeen, H., Weigle, M.C., Nelson, M.L.: How much of the web is archived? In: Proceedings of JCDL \u201911, pp. 133\u2013136 (2011)","DOI":"10.1145\/1998076.1998100"},{"key":"108_CR12","doi-asserted-by":"crossref","unstructured":"Adar, E., Teevan, J., Dumais, S.T., Elsas, J.L.: The web changes everything: understanding the dynamics of web content. In: Proceedings of WSDM \u201909, pp. 282\u2013291 (2009)","DOI":"10.1145\/1498759.1498837"},{"key":"108_CR13","unstructured":"Cho, J., Garcia-Molina, H.: The evolution of the web and implications for an incremental crawler. In: Proceedings of VLDB \u201900, pp. 200\u2013209 (2000)"},{"key":"108_CR14","doi-asserted-by":"publisher","first-page":"256","DOI":"10.1145\/857166.857170","volume":"3","author":"J Cho","year":"2003","unstructured":"Cho, J., Garcia-Molina, H.: Estimating frequency of change. ACM Trans. Internet Technol. 3, 256\u2013290 (2003)","journal-title":"ACM Trans. Internet Technol."},{"key":"108_CR15","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. In: Proceedings of JCDL \u201904, pp. 160\u2013168 (2004)","DOI":"10.1145\/996350.996387"},{"key":"108_CR16","doi-asserted-by":"crossref","unstructured":"Fetterly, D., Manasse, M., Najork, M., Wiener, J.: A large-scale study of the evolution of web pages. In: Proceedings of WWW \u201903, pp. 669\u2013678 (2003)","DOI":"10.1145\/775152.775246"},{"key":"108_CR17","doi-asserted-by":"crossref","unstructured":"Lim, L., Wang, M., Padmanabhan, S., Vitter, J.S., Agarwal, R.C.: Characterizing web document change. In: Proceedings of WAIM \u201901, pp. 133\u2013144 (2001)","DOI":"10.1007\/3-540-47714-4_13"},{"key":"108_CR18","doi-asserted-by":"crossref","unstructured":"Ntoulas, A., Cho, J., Olston, C.: What\u2019s new on the web?: the evolution of the web from a search engine perspective. In: Proceedings of WWW \u201904, pp. 1\u201312 (2004)","DOI":"10.1145\/988672.988674"},{"issue":"3","key":"108_CR19","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. 32(3), 201\u2013212 (2000)","journal-title":"ACM Comput. Surv."},{"key":"108_CR20","doi-asserted-by":"crossref","unstructured":"Ashman, H., Davis, H., Whitehead, J., Caughey, S.: Missing the 404: link integrity on the world wide web. In: Proceedings of WWW \u201998, pp. 761\u2013762 (1998)","DOI":"10.1016\/S0169-7552(98)00131-7"},{"key":"108_CR21","doi-asserted-by":"crossref","unstructured":"Davis, H.C.: Referential integrity of links in open hypermedia systems. In: Proceedings of HYPERTEXT \u201998, pp. 207\u2013216 (1998)","DOI":"10.1145\/276627.276650"},{"key":"108_CR22","doi-asserted-by":"publisher","unstructured":"Davis, H.C.: Hypertext Link Integrity. ACM Comput. Surv. 31 (1999). doi: 10.1145\/345966.346026","DOI":"10.1145\/345966.346026"},{"key":"108_CR23","unstructured":"Johnson, D., Tanimoto, S.: Reusing web documents in tutorials with the current-documents assumption: automatic validation of updates. In: Proceedings of EDMEDIA\u201999, pp. 74\u201379 (1999)"},{"key":"108_CR24","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. Sci. Am. 276, 82\u201383 (1997)","journal-title":"Sci. Am."},{"issue":"2","key":"108_CR25","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1109\/2.901164","volume":"34","author":"S Lawrence","year":"2001","unstructured":"Lawrence, S., Pennock, D.M., Flake, G.W., Krovetz, R., Coetzee, F.M., Glover, E., Nielsen, F.A., Kruger, A., Giles, C.L.: Persistence of web references in scientific research. Computer 34(2), 26\u201331 (2001)","journal-title":"Computer"},{"issue":"2","key":"108_CR26","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1002\/asi.10018","volume":"53","author":"WC Koehler","year":"2002","unstructured":"Koehler, W.C.: Web page change and persistence\u2014a four-year longitudinal study. J. Am. Soc. Inf. Sci. Technol. 53(2), 162\u2013171 (2002)","journal-title":"J. Am. Soc. Inf. Sci. Technol."},{"issue":"1","key":"108_CR27","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 46(1), 71\u201377 (2003). doi: 10.1145\/602421.602422","journal-title":"Commun. ACM"},{"issue":"5646","key":"108_CR28","doi-asserted-by":"publisher","first-page":"787","DOI":"10.1126\/science.1088234","volume":"302","author":"RP Dellavalle","year":"2003","unstructured":"Dellavalle, R.P., Hester, E.J., Heilig, L.F., Drake, A.L., Kuntzman, J.W., Graber, M., Schilling, L.M.: Information science: going, going, gone: lost internet references. Science 302(5646), 787\u2013788 (2003). doi: 10.1126\/science.1088234","journal-title":"Science"},{"key":"108_CR29","unstructured":"McCown, F., Chan, S., Nelson, M.L., Bollen, J.: The availability and persistence of web references in D-Lib magazine. In: Proceedings of IWAW\u201905 (2005)"},{"key":"108_CR30","doi-asserted-by":"publisher","unstructured":"Nelson, M.L., Allen, B.D.: Object persistence and availability in digital libraries. D Lib Mag. 8(1) (2002). doi: 10.1045\/january2002-nelson","DOI":"10.1045\/january2002-nelson"},{"key":"108_CR31","unstructured":"Sanderson, R., Phillips, M., Van de Sompel, H.: Analyzing the persistence of referenced web resources with memento. In: Proceedings of OR \u201911 (2011)"},{"key":"108_CR32","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. In: Proceedings of WWW \u201904, pp. 328\u2013337 (2004)","DOI":"10.1145\/988672.988716"},{"key":"108_CR33","doi-asserted-by":"crossref","unstructured":"Lee, T., Kim, J., Kim, J.W., Kim, S.R., Park, K.: Detecting soft errors by redirection classification. In: Proceedings of WWW \u201909, pp. 1119\u20131120 (2009)","DOI":"10.1145\/1526709.1526886"},{"key":"108_CR34","doi-asserted-by":"crossref","unstructured":"Meneses, L., Furuta, R., Shipman, F.: Identifying \u201cSoft 404\u201d error pages: analyzing the lexical signatures of documents in distributed collections. In: Proceedings of TPDL\u2019 12 (2012)","DOI":"10.1007\/978-3-642-33290-6_22"},{"key":"108_CR35","doi-asserted-by":"crossref","unstructured":"Fielding, R., Gettys, J., Mogul, J., Frystyk, H., Masinter, L., Leach, P., Berners-Lee, T.: Hypertext Transfer Protocol-HTTP\/1.1 RFC-2612. Updated by RFC 2817 (1999)","DOI":"10.17487\/rfc2616"},{"key":"108_CR36","doi-asserted-by":"crossref","unstructured":"Martinez-Romo, J., Araujo, L.: Recommendation system for automatic recovery of broken web links. In: Proceedings of IBERAMIA \u201908, pp. 302\u2013311 (2008)","DOI":"10.1007\/978-3-540-88309-8_31"},{"key":"108_CR37","doi-asserted-by":"crossref","unstructured":"Martinez-Romo, J., Araujo, L.: Retrieving broken web links using an approach based on contextual information. In: Proceedings of HT \u201909, pp. 351\u2013352 (2009)","DOI":"10.1145\/1557914.1557984"},{"key":"108_CR38","doi-asserted-by":"crossref","unstructured":"Martinez-Romo, J., Araujo, L.: Analyzing information retrieval methods to recover broken web links. In: Proceedings of ECIR \u201910, pp. 26\u201337 (2010)","DOI":"10.1007\/978-3-642-12275-0_6"},{"key":"108_CR39","doi-asserted-by":"crossref","unstructured":"Francisco-Revilla, L., Shipman, F., Furuta, R., Karadkar, U., Arora, A.: Managing change on the web. In: Proceedings of JCDL \u201901, pp. 67\u201376 (2001)","DOI":"10.1145\/379437.379973"},{"key":"108_CR40","doi-asserted-by":"crossref","unstructured":"Bogen, P., Pogue, D., Poursardar, F., Shipman, F., Furuta, R.: WPv4: A re-imagined Waldens paths to support diverse user communities. In: Proceedings of JCDL \u201911 (2011)","DOI":"10.1145\/1998076.1998164"},{"key":"108_CR41","doi-asserted-by":"crossref","unstructured":"Harrison, T.L., Nelson, M.L.: Just-in-time recovery of missing web pages. In: Proceedings of HYPERTEXT \u201906, pp. 145\u2013156 (2006)","DOI":"10.1145\/1149941.1149971"},{"key":"108_CR42","doi-asserted-by":"crossref","unstructured":"Haslhofer, B., Popitsch, N.: DSNotify\u2014detecting and fixing broken links in linked data sets. In: Proceedings of DEXA \u201909, pp. 89\u201393 (2009)","DOI":"10.1109\/DEXA.2009.13"},{"key":"108_CR43","doi-asserted-by":"crossref","unstructured":"Popitsch, N.P., Haslhofer, B.: DSNotify: Handling broken links in the web of data. In: Proceedings of WWW \u201910, pp. 761\u2013770 (2010)","DOI":"10.1145\/1772690.1772768"},{"issue":"11","key":"108_CR44","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1016\/0020-0271(73)90043-0","volume":"9","author":"KS Jones","year":"1973","unstructured":"Jones, K.S.: Index Term Weighting. Inf. Storage Retr. 9(11), 619\u2013633 (1973)","journal-title":"Inf. Storage Retr."},{"issue":"4","key":"108_CR45","doi-asserted-by":"publisher","first-page":"540","DOI":"10.1145\/1028099.1028101","volume":"22","author":"ST 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. 22(4), 540\u2013572 (2004). doi: 10.1145\/1028099.1028101","journal-title":"ACM Trans. Inf. Syst."},{"key":"108_CR46","volume-title":"Modern Information Retrieval","author":"RA Baeza-Yates","year":"1999","unstructured":"Baeza-Yates, R.A., Ribeiro-Neto, B.: Modern Information Retrieval. Addison-Wesley Longman Publishing Co., Inc, Boston (1999)"},{"key":"108_CR47","unstructured":"Frakes, W.B., Baeza-Yates, R.A. (eds.): Information Retrieval: Data Structures and Algorithms. Prentice-Hall, Englewood Clifs (1992)"},{"key":"108_CR48","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809071","volume-title":"Introduction to Information Retrieval","author":"CD Manning","year":"2008","unstructured":"Manning, C.D., Raghavan, P., Schtze, H.: Introduction to Information Retrieval. Cambridge University Press, New York (2008)"},{"key":"108_CR49","doi-asserted-by":"crossref","unstructured":"Robertson, S.E., Walker, S.: Some simple effective approximations to the 2-Poisson model for probabilistic weighted retrieval. In: Proceedings of SIGIR \u201994, pp. 232\u2013241 (1994)","DOI":"10.1007\/978-1-4471-2099-5_24"},{"issue":"5","key":"108_CR50","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1016\/0306-4573(88)90021-0","volume":"24","author":"G Salton","year":"1988","unstructured":"Salton, G., Buckley, C.: Term-weighting approaches in automatic text retrieval. Inf. Process. Manag. 24(5), 513\u2013523 (1988). doi: 10.1016\/0306-4573(88)90021-0","journal-title":"Inf. Process. Manag."},{"key":"108_CR51","doi-asserted-by":"crossref","unstructured":"Klein, M., Nelson, M.L.: A Comparison of techniques for estimating IDF values to generate lexical signatures for the web. In: Proceeding of WIDM \u201908, pp. 39\u201346 (2008)","DOI":"10.1145\/1458502.1458510"},{"key":"108_CR52","unstructured":"The size of the World Wide Web. http:\/\/www.worldwidewebsize.com\/"},{"key":"108_CR53","unstructured":"Phelps, T.A., Wilensky, R.: Robust Hyperlinks Cost Just Five Words Each. Tech. Rep. UCB\/\/CSD-00-1091, University of California at Berkeley, Berkeley, CA, USA (2000)"},{"key":"108_CR54","unstructured":"Phelps, T.A., Wilensky, R.: Robust hyperlinks: cheap, everywhere, now. In: Proceedings of DDEP\u201900 (2000)"},{"key":"108_CR55","doi-asserted-by":"crossref","unstructured":"McCown, F., Nelson, M.L.: agreeing to disagree: search engines and their public interfaces. In: Proceedings of JCDL \u201907, pp. 309\u2013318 (2007)","DOI":"10.1145\/1255175.1255237"},{"key":"108_CR56","doi-asserted-by":"crossref","unstructured":"Agichtein, E., Zheng, Z.: Identifying \u201cBest Bet\u201d web search results by mining past user behavior. In: Proceedings of KDD \u201906, pp. 902\u2013908 (2006)","DOI":"10.1145\/1150402.1150526"},{"issue":"2","key":"108_CR57","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1016\/S0306-4573(99)00056-4","volume":"36","author":"BJ Jansen","year":"2000","unstructured":"Jansen, B.J., Spink, A., Saracevic, T.: Real life, real users, and real needs: a study and analysis of user queries on the web. Inf. Process. Manag. 36(2), 207\u2013227 (2000). doi: 10.1016\/S0306-4573(99)00056-4","journal-title":"Inf. Process. Manag."},{"key":"108_CR58","doi-asserted-by":"crossref","unstructured":"Joachims, T., Granka, L., Pan, B., Hembrooke, H., Gay, G.: Accurately interpreting clickthrough data as implicit feedback. In: Proceedings of SIGIR \u201905, pp. 154\u2013161 (2005)","DOI":"10.1145\/1076034.1076063"},{"issue":"2","key":"108_CR59","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1145\/1229179.1229181","volume":"25","author":"T Joachims","year":"2007","unstructured":"Joachims, T., Granka, L., Pan, B., Hembrooke, H., Radlinski, F., Gay, G.: Evaluating the accuracy of implicit feedback from clicks and query reformulations in web search. ACM Trans. Inf. Syst. 25(2), 7 (2007). doi: 10.1145\/1229179.1229181","journal-title":"ACM Trans. Inf. Syst."},{"key":"108_CR60","doi-asserted-by":"crossref","unstructured":"Kl\u00f6ckner, K., Wirschum, N., Jameson, A.: Depth- and breadth-first processing of search result lists. In: Proceedings of CHI \u201904, pp. 1539\u20131539 (2004)","DOI":"10.1145\/985921.986115"},{"issue":"4","key":"108_CR61","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1145\/582415.582418","volume":"20","author":"K J\u00e4rvelin","year":"2002","unstructured":"J\u00e4rvelin, K., Kek\u00e4l\u00e4inen, J.: Cumulated gain-based evaluation of IR techniques. ACM Trans. Inf. Syst. 20(4), 422\u2013446 (2002)","journal-title":"ACM Trans. Inf. Syst."},{"key":"108_CR62","doi-asserted-by":"crossref","unstructured":"Chakrabarti, D., Kumar, R., Punera, K.: Generating succinct titles for web URLs. In: Proceeding of KDD \u201908, pp. 79\u201387 (2008)","DOI":"10.1145\/1401890.1401905"},{"key":"108_CR63","doi-asserted-by":"crossref","unstructured":"Klein, M., Shipman, J., Nelson, M.L.: Is this a good title? In: Proceedings of Hypertext \u201910, pp. 3\u201312 (2010)","DOI":"10.1145\/1810617.1810621"},{"issue":"8","key":"108_CR64","first-page":"707","volume":"10","author":"VI Levenshtein","year":"1966","unstructured":"Levenshtein, V.I.: Binary codes capable of correcting deletions. Inser. Reversals Soviet Physics Doklady 10(8), 707\u2013710 (1966)","journal-title":"Inser. Reversals Soviet Physics Doklady"},{"key":"108_CR65","doi-asserted-by":"crossref","unstructured":"Bao, S., Xue, G., Wu, X., Yu, Y., Fei, B., Su, Z.: Optimizing web search using social annotations. In: Proceedings of WWW \u201907, pp. 501\u2013510 (2007)","DOI":"10.1145\/1242572.1242640"},{"issue":"4","key":"108_CR66","doi-asserted-by":"crossref","first-page":"1562","DOI":"10.1016\/j.ipm.2007.12.010","volume":"44","author":"P. Jason Morrison","year":"2008","unstructured":"Jason Morrison, P.: Tagging and searching: search retrieval effectiveness of folksonomies on the world wide web. Inf. Process. Manag. 44(4), 1562\u20131579 (2008)","journal-title":"Inf. Process. Manag."},{"key":"108_CR67","doi-asserted-by":"crossref","unstructured":"Heymann, P., Koutrika, G., Garcia-Molina, H.: Can social bookmarking improve web search? In: Proceedings of WSDM \u201908, pp. 195\u2013206 (2008)","DOI":"10.1145\/1341531.1341558"},{"key":"108_CR68","doi-asserted-by":"crossref","unstructured":"Bischoff, K., Firan, C., Nejdl, W., Paiu, R.: Can all tags be used for search? In: Proceedings of CIKM \u201908, pp. 193\u2013202 (2008)","DOI":"10.1145\/1458082.1458112"},{"key":"108_CR69","unstructured":"Delicious Integrated Into Yahoo Search Results. http:\/\/techcrunch.com\/2008\/01\/19\/delicious-integrated-into-yahoo-search-results\/"},{"key":"108_CR70","unstructured":"Klein, M.: Adventures with the delicious API. http:\/\/ws-dl.blogspot.com\/2011\/03\/2011-03-09-adventures-with-delicious.html"},{"key":"108_CR71","doi-asserted-by":"crossref","unstructured":"Klein, M., Nelson, M.L.: Evaluating methods to rediscover missing web pages from the web infrastructure. In: Proceedings of JCDL \u201910, pp. 59\u201368 (2010)","DOI":"10.1145\/1816123.1816133"},{"key":"108_CR72","doi-asserted-by":"crossref","unstructured":"Craswell, N., Hawking, D., Robertson, S.: Effective site finding using link anchor information. In: Proceedings of SIGIR \u201901, pp. 250\u2013257 (2001)","DOI":"10.1145\/383952.383999"},{"key":"108_CR73","doi-asserted-by":"crossref","unstructured":"Dou, Z., Song, R., Nie, J.Y., Wen, J.R.: Using anchor texts with their hyperlink structure for web search. In: Proceedings of SIGIR \u201909, pp. 227\u2013234 (2009)","DOI":"10.1145\/1571941.1571982"},{"key":"108_CR74","doi-asserted-by":"crossref","unstructured":"Kraft, R., Zien, J.: Mining anchor text for query refinement. In: Proceedings of WWW \u201904, pp. 666\u2013674 (2004)","DOI":"10.1145\/988672.988763"},{"key":"108_CR75","doi-asserted-by":"crossref","unstructured":"Klein, M., Ware, J., Nelson, M.L.: Rediscovering missing web pages using link neighborhood lexical signatures. In: Proceedings of JCDL \u201911, pp. 137\u2013140 (2011)","DOI":"10.1145\/1998076.1998101"},{"key":"108_CR76","doi-asserted-by":"crossref","unstructured":"Ware, J., Klein, M., Nelson, M.L.: Rediscovering missing web pages using link neighborhood lexical signatures. Tech. Rep. arXiv:1102.0930v1, CS Department, Old Dominion University, Norfolk, Virginia, USA (2011)","DOI":"10.1145\/1998076.1998101"},{"key":"108_CR77","unstructured":"The ClueWeb12 Dataset. http:\/\/lemurproject.org\/clueweb12\/"},{"key":"108_CR78","unstructured":"Common Crawl Foundation. http:\/\/commoncrawl.org\/"}],"container-title":["International Journal on Digital Libraries"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00799-014-0108-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00799-014-0108-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00799-014-0108-0","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00799-014-0108-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,7]],"date-time":"2019-08-07T05:51:18Z","timestamp":1565157078000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00799-014-0108-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,2,1]]},"references-count":78,"journal-issue":{"issue":"1-2","published-print":{"date-parts":[[2014,4]]}},"alternative-id":["108"],"URL":"https:\/\/doi.org\/10.1007\/s00799-014-0108-0","relation":{},"ISSN":["1432-5012","1432-1300"],"issn-type":[{"value":"1432-5012","type":"print"},{"value":"1432-1300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,2,1]]}}}