{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:46:43Z","timestamp":1750308403369,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,7,13]],"date-time":"2020-07-13T00:00:00Z","timestamp":1594598400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"German Federal Ministry of Education and Research (BMBF)","award":["01PU17012D"],"award-info":[{"award-number":["01PU17012D"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,7,13]]},"DOI":"10.1145\/3372923.3404836","type":"proceedings-article","created":{"date-parts":[[2020,7,9]],"date-time":"2020-07-09T15:51:46Z","timestamp":1594309906000},"page":"85-89","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["How to Assess the Exhaustiveness of Longitudinal Web Archives"],"prefix":"10.1145","author":[{"given":"Michael","family":"Paris","sequence":"first","affiliation":[{"name":"Humboldt-Universit\u00e4t zu Berlin, Berlin, Germany"}]},{"given":"Robert","family":"J\u00e4schke","sequence":"additional","affiliation":[{"name":"Humboldt-Universit\u00e4t zu Berlin, Berlin, Germany"}]}],"member":"320","published-online":{"date-parts":[[2020,7,13]]},"reference":[{"volume-title":"Proc. WSDM. ACM. https:\/\/doi.org\/10","author":"Adar E.","key":"e_1_3_2_1_1_1","unstructured":"E. Adar , J. Teevan , S. T. Dumais , and J. L. Elsas . 2009. The web changes everything . In Proc. WSDM. ACM. https:\/\/doi.org\/10 .1145\/1498759.1498837 E. Adar, J. Teevan, S. T. Dumais, and J. L. Elsas. 2009. The web changes everything. In Proc. WSDM. ACM. https:\/\/doi.org\/10.1145\/1498759.1498837"},{"volume-title":"Proc. Hypertext. ACM. https:\/\/doi.org\/10","author":"Ainsworth S. G.","key":"e_1_3_2_1_2_1","unstructured":"S. G. Ainsworth , M. L. Nelson , and H. Van de Sompel. 2015. Only One Out of Five Archived Web Pages Existed as Presented . In Proc. Hypertext. ACM. https:\/\/doi.org\/10 .1145\/2700171.2791044 S. G. Ainsworth, M. L. Nelson, and H. Van de Sompel. 2015. Only One Out of Five Archived Web Pages Existed as Presented. In Proc. Hypertext. ACM. https:\/\/doi.org\/10.1145\/2700171.2791044"},{"volume-title":"Proc. Int. Workshop on Algorithms and Models for the Web-Graph. 156--167","author":"Baeza-Yates R. A.","key":"e_1_3_2_1_3_1","unstructured":"R. A. Baeza-Yates and C. Castillo . 2004. Crawling the Infinite Web: Five Levels Are Enough . In Proc. Int. Workshop on Algorithms and Models for the Web-Graph. 156--167 . https:\/\/doi.org\/10.1007\/978-3-540-30216-2_13 R. A. Baeza-Yates and C. Castillo. 2004. Crawling the Infinite Web: Five Levels Are Enough. In Proc. Int. Workshop on Algorithms and Models for the Web-Graph. 156--167. https:\/\/doi.org\/10.1007\/978-3-540-30216-2_13"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1080\/24701475.2019.1654290"},{"key":"e_1_3_2_1_5_1","volume-title":"Proc. Int. Conf. Data Mining \/ ICDM Workshops (2008","author":"Bordino I.","year":"2008","unstructured":"I. Bordino , P. Boldi , D. Donato , M. Santini , and S. Vigna . 2008. Temporal evolution of the UK web . Proc. Int. Conf. Data Mining \/ ICDM Workshops (2008 ), 909--918. https:\/\/doi.org\/10.1109\/ICDMW. 2008 .88 I. Bordino, P. Boldi, D. Donato, M. Santini, and S. Vigna. 2008. Temporal evolution of the UK web. Proc. Int. Conf. Data Mining \/ ICDM Workshops (2008), 909--918. https:\/\/doi.org\/10.1109\/ICDMW.2008.88"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/2.781636"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1389-1286(99)00052-3"},{"volume-title":"Proc. VLDB. 200--209","author":"Cho J.","key":"e_1_3_2_1_8_1","unstructured":"J. Cho and H. Garcia-Molina . 2000. The Evolution of the Web and Implications for an Incremental Crawler . In Proc. VLDB. 200--209 . J. Cho and H. Garcia-Molina. 2000. The Evolution of the Web and Implications for an Incremental Crawler. In Proc. VLDB. 200--209."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.im.2006.11.003"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1002\/asi.20078"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-011-0219-9"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of 27th International Conference on Very Large Data Bases. 321--329","author":"Ester M.","year":"2001","unstructured":"M. Ester , M. Gro\u00df , and H.-P. Kriegel . 2001 . Focused Web Crawling: A Generic Framework for Specifying the User Interest and for Adaptive Crawling Strategies . In Proceedings of 27th International Conference on Very Large Data Bases. 321--329 . M. Ester, M. Gro\u00df, and H.-P. Kriegel. 2001. Focused Web Crawling: A Generic Framework for Specifying the User Interest and for Adaptive Crawling Strategies. In Proceedings of 27th International Conference on Very Large Data Bases. 321--329."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/504216.504267"},{"key":"e_1_3_2_1_14_1","unstructured":"G. Grefenstette and L. Muchemi. 2016. Determining the Characteristic Vocabulary for a Specialized Dictionary using Word2vec and a Directed Crawler. CoRR Vol. abs\/1605.09564 (2016). arxiv: 1605.09564  G. Grefenstette and L. Muchemi. 2016. Determining the Characteristic Vocabulary for a Specialized Dictionary using Word2vec and a Directed Crawler. CoRR Vol. abs\/1605.09564 (2016). arxiv: 1605.09564"},{"key":"e_1_3_2_1_15_1","volume-title":"The WARC Format 1.1 . https:\/\/iipc.github.io\/warc-specifications\/specifications\/warc-format\/warc-1.1\/#warc-file-name-size-and-compression. Online","author":"International Internet Preservation Consortium (IIPC). [n.d.].","year":"2020","unstructured":"International Internet Preservation Consortium (IIPC). [n.d.]. The WARC Format 1.1 . https:\/\/iipc.github.io\/warc-specifications\/specifications\/warc-format\/warc-1.1\/#warc-file-name-size-and-compression. Online ; Last accessed 1 Apr 2020 . International Internet Preservation Consortium (IIPC). [n.d.]. The WARC Format 1.1 . https:\/\/iipc.github.io\/warc-specifications\/specifications\/warc-format\/warc-1.1\/#warc-file-name-size-and-compression. Online; Last accessed 1 Apr 2020."},{"key":"e_1_3_2_1_16_1","volume-title":"Heritrix -- The Internet Archive's open-source, extensible, web-scale, archival-quality web crawler project. https:\/\/github.com\/internetarchive\/heritrix3. [Online","author":"Archive Internet","year":"2020","unstructured":"Internet Archive . [n.d.]. Heritrix -- The Internet Archive's open-source, extensible, web-scale, archival-quality web crawler project. https:\/\/github.com\/internetarchive\/heritrix3. [Online ; Last accessed 1 Apr 2020 ]. Internet Archive. [n.d.]. Heritrix -- The Internet Archive's open-source, extensible, web-scale, archival-quality web crawler project. https:\/\/github.com\/internetarchive\/heritrix3. [Online; Last accessed 1 Apr 2020]."},{"volume-title":"Pro. Int. Conf. Information and Knowledge Management -- CIKM. ACM Press. https:\/\/doi.org\/10","author":"Liben-Nowell D.","key":"e_1_3_2_1_17_1","unstructured":"D. Liben-Nowell and J. Kleinberg . 2003. The link prediction problem for social networks . In Pro. Int. Conf. Information and Knowledge Management -- CIKM. ACM Press. https:\/\/doi.org\/10 .1145\/956863.956972 D. Liben-Nowell and J. Kleinberg. 2003. The link prediction problem for social networks. In Pro. Int. Conf. Information and Knowledge Management -- CIKM. ACM Press. https:\/\/doi.org\/10.1145\/956863.956972"},{"key":"e_1_3_2_1_18_1","first-page":"988674","article-title":"What's New on the Web? The Evolution of the Web from a Search Engine Perspective. In","volume":"1145","author":"Ntoulas A.","year":"2004","unstructured":"A. Ntoulas , J. Cho , and C. Olston . 2004 . What's New on the Web? The Evolution of the Web from a Search Engine Perspective. In Proc. Int. Conf. World Wide Web. ACM, 1--12. https:\/\/doi.org\/10. 1145\/988672 . 988674 A. Ntoulas, J. Cho, and C. Olston. 2004. What's New on the Web? The Evolution of the Web from a Search Engine Perspective. In Proc. Int. Conf. World Wide Web. ACM, 1--12. https:\/\/doi.org\/10.1145\/988672.988674","journal-title":"Proc. Int. Conf. World Wide Web. ACM, 1--12. https:\/\/doi.org\/10."},{"key":"e_1_3_2_1_19_1","unstructured":"Michael Paris and Robert J\u00e4schke. 2020. Summary GAW. https:\/\/doi.org\/10.5281\/zenodo.3843507  Michael Paris and Robert J\u00e4schke. 2020. Summary GAW. https:\/\/doi.org\/10.5281\/zenodo.3843507"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1177\/0165551507079417"},{"volume-title":"Proc. 3rd Workshop on Information Credibility on the Web (WICOW '09)","author":"Spaniol M.","key":"e_1_3_2_1_21_1","unstructured":"M. Spaniol , D. Denev , A. Mazeika , G. Weikum , and P. Senellart . 2009. Data Quality in Web Archiving . In Proc. 3rd Workshop on Information Credibility on the Web (WICOW '09) . ACM, 19--26. https:\/\/doi.org\/10.1145\/1526993.1526999 M. Spaniol, D. Denev, A. Mazeika, G. Weikum, and P. Senellart. 2009. Data Quality in Web Archiving. In Proc. 3rd Workshop on Information Credibility on the Web (WICOW '09). ACM, 19--26. https:\/\/doi.org\/10.1145\/1526993.1526999"},{"volume-title":"Pro. Conf. Innovative Data Systems Research. 199--202","author":"Weikum G.","key":"e_1_3_2_1_22_1","unstructured":"G. Weikum , N. Ntarmos , M. Spaniol , P. Triantafillou , A. Bencz\u00far , S. Kirkpatrick , P. Rigaux , and M. Williamson . 2011. Longitudinal Analytics on Web Archive Data: It's About Time! . In Pro. Conf. Innovative Data Systems Research. 199--202 . G. Weikum, N. Ntarmos, M. Spaniol, P. Triantafillou, A. Bencz\u00far, S. Kirkpatrick, P. Rigaux, and M. Williamson. 2011. Longitudinal Analytics on Web Archive Data: It's About Time!. In Pro. Conf. Innovative Data Systems Research. 199--202."}],"event":{"name":"HT '20: 31st ACM Conference on Hypertext and Social Media","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGCHI ACM Special Interest Group on Computer-Human Interaction"],"location":"Virtual Event USA","acronym":"HT '20"},"container-title":["Proceedings of the 31st ACM Conference on Hypertext and Social Media"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3372923.3404836","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3372923.3404836","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T17:45:19Z","timestamp":1750268719000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3372923.3404836"}},"subtitle":["A Case Study of the German Academic Web"],"short-title":[],"issued":{"date-parts":[[2020,7,13]]},"references-count":22,"alternative-id":["10.1145\/3372923.3404836","10.1145\/3372923"],"URL":"https:\/\/doi.org\/10.1145\/3372923.3404836","relation":{},"subject":[],"published":{"date-parts":[[2020,7,13]]},"assertion":[{"value":"2020-07-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}