{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T04:11:30Z","timestamp":1748751090680,"version":"3.41.0"},"publisher-location":"Cham","reference-count":14,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319256597"},{"type":"electronic","value":"9783319256603"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-25660-3_7","type":"book-chapter","created":{"date-parts":[[2015,11,25]],"date-time":"2015-11-25T12:11:58Z","timestamp":1448453518000},"page":"78-90","source":"Crossref","is-referenced-by-count":0,"title":["A Simhash-Based Generalized Framework for Citation Matching in MapReduce"],"prefix":"10.1007","author":[{"given":"Pengsen","family":"Wang","sequence":"first","affiliation":[]},{"given":"Bin","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Xiaoming","family":"Li","sequence":"additional","affiliation":[]},{"given":"Lin","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Bai","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,11,26]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Councill, I.G., Li, H., Zhuang, Z., et al.: Learning metadata from the evidence in an on-line citation matching scheme. In: JCDL, pp. 276\u2013285 (2006)","key":"7_CR1","DOI":"10.1145\/1141753.1141817"},{"unstructured":"Pasula, H., Marthi, B., Milch, B., et al.: Identity uncertainty and citation matching. In: Advances in Neural Information Processing Systems, pp. 1425\u20131432 (2003)","key":"7_CR2"},{"doi-asserted-by":"crossref","unstructured":"Charikar, M.S.: Similarity estimation techniques from rounding algorithms. In: STOC, pp. 380\u2013388 (2002)","key":"7_CR3","DOI":"10.1145\/509907.509965"},{"doi-asserted-by":"crossref","unstructured":"Hitchcock, S., et al.: Citation linking: improving access to online journals. In: Proceedings of the Second ACM International Conference on Digital Libraries, pp. 115\u2013122 (1997)","key":"7_CR4","DOI":"10.1145\/263690.263804"},{"key":"7_CR5","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1007\/978-3-540-89378-3_61","volume-title":"AI 2008: Advances in Artificial Intelligence","author":"Z Liao","year":"2008","unstructured":"Liao, Z., Zhang, Z.: A generalized joint inference approach for citation matching. In: Wobcke, W., Zhang, M. (eds.) AI 2008. LNCS (LNAI), vol. 5360, pp. 601\u2013607. Springer, Heidelberg (2008)"},{"doi-asserted-by":"crossref","unstructured":"Koo, H.K., Kim, T., Chun, H.W., et al.: Effects of unpopular citation fields in citation matching performance. In: ICISA, pp. 1\u20137 (2011)","key":"7_CR6","DOI":"10.1109\/ICISA.2011.5772372"},{"issue":"2","key":"7_CR7","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1145\/1314215.1314231","volume":"51","author":"MY Kan","year":"2008","unstructured":"Kan, M.Y., Tan, Y.F.: Record matching in digital library metadata. Commun. ACM 51(2), 91\u201394 (2008)","journal-title":"Commun. ACM"},{"doi-asserted-by":"crossref","unstructured":"Manku, G.S., Jain, A., Das Sarma, A.: Detecting near-duplicates for web crawling. In: WWW, pp. 141\u2013150 (2007)","key":"7_CR8","DOI":"10.1145\/1242572.1242592"},{"key":"7_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"362","DOI":"10.1007\/978-3-642-40501-3_37","volume-title":"Research and Advanced Technology for Digital Libraries","author":"M Fedoryszak","year":"2013","unstructured":"Fedoryszak, M., Tkaczyk, D., Bolikowski, \u0141.: Large scale citation matching using Apache Hadoop. In: Aalberg, T., Papatheodorou, C., Dobreva, M., Tsakonas, G., Farrugia, C.J. (eds.) TPDL 2013. LNCS, vol. 8092, pp. 362\u2013365. Springer, Heidelberg (2013)"},{"doi-asserted-by":"crossref","unstructured":"Liu, Y., Wu, Q., Han, Y., et al.: The fingerprint analysis technique-oriented research on microblog for public opinion analysis. In: ICIMCS, pp. 372\u2013375 (2013)","key":"7_CR10","DOI":"10.1145\/2499788.2499868"},{"doi-asserted-by":"crossref","unstructured":"Pham, T.A.N, Nguyen, V.K.: A simhash-based scheme for locating product information from the web. In: SoICT, pp. 199\u2013206 (2011)","key":"7_CR11","DOI":"10.1145\/2069216.2069254"},{"doi-asserted-by":"crossref","unstructured":"Bilenko, M., Mooney, R.J.: Adaptive duplicate detection using learnable string similarity measures. In: KDD, pp. 39\u201348 (2003)","key":"7_CR12","DOI":"10.1145\/956750.956759"},{"doi-asserted-by":"crossref","unstructured":"McCallun, A., Nigam, K., Ungar, L.: Efficient clustering of high-dimensional data sets with application to reference clustering. In: KDD, pp. 169\u2013179 (2000)","key":"7_CR13","DOI":"10.1145\/347090.347123"},{"doi-asserted-by":"crossref","unstructured":"Chierichetti, F., Dalvi, N., Kumar, R.: Correlation clustering in MapReduce. In: KDD, pp. 641\u2013650 (2014)","key":"7_CR14","DOI":"10.1145\/2623330.2623743"}],"container-title":["Lecture Notes in Computer Science","Trends and Applications in Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-25660-3_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T14:38:20Z","timestamp":1748702300000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-25660-3_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319256597","9783319256603"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-25660-3_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2015]]}}}