{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T18:47:01Z","timestamp":1781808421963,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":19,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,5,8]]},"DOI":"10.1145\/3701716.3715303","type":"proceedings-article","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T14:10:32Z","timestamp":1750687832000},"page":"745-748","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Benchmarking Near-Duplicate Detection in the era of Pay-walled News"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-9602-7640","authenticated-orcid":false,"given":"Alok","family":"Kumar","sequence":"first","affiliation":[{"name":"TCS Research, Pune, Maharashtra, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1438-6036","authenticated-orcid":false,"given":"Siddharth","family":"Tumre","sequence":"additional","affiliation":[{"name":"TCS Research, Pune, Maharashtra, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9452-1397","authenticated-orcid":false,"given":"Sangameshwar","family":"Patil","sequence":"additional","affiliation":[{"name":"TCS Research, Pune, Maharshtra, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,5,23]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Proc. of 18th Intl. Conf. on NLP.","author":"Bedi H.","unstructured":"H. Bedi, S. Patil, and G.K. Palshikar. 2021. Temporal question generation from history text. In Proc. of 18th Intl. Conf. on NLP."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/829502.830043"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45123-4_1"},{"key":"e_1_3_2_2_4_1","volume-title":"Proc. of 30th ACM Symp. on Theory of Computing. ACM.","author":"Broder A.","unstructured":"A. Broder, M. Charikar, A. Frieze, and M. Mitzenmacher. 1998. Min-Wise Independent Permutations. In Proc. of 30th ACM Symp. on Theory of Computing. ACM."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/509907.509965"},{"key":"e_1_3_2_2_6_1","volume-title":"A coefficient of agreement for nominal scales. Educational and psychological measurement","author":"Cohen Jacob","year":"1960","unstructured":"Jacob Cohen. 1960. A coefficient of agreement for nominal scales. Educational and psychological measurement, Vol. 20, 1 (1960), 37--46."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.4337\/9780857939135"},{"key":"e_1_3_2_2_8_1","volume-title":"Proc. of 16th Intl. Conf. on WWW.","author":"Das A. S.","unstructured":"A. S. Das, M. Datar, A. Garg, and S. Rajaram. 2007. Google News Personalization: Scalable Online Collaborative Filtering. In Proc. of 16th Intl. Conf. on WWW."},{"key":"e_1_3_2_2_9_1","volume-title":"Proc. of 9th Intl. Workshop on News Recommendation and Analytics (RecSys).","author":"Gedikli F.","unstructured":"F. Gedikli, A. S. Novo, and D. Jannach. 2021. Semi-automated identification of news story chains: A new dataset and entity-based labeling method. In Proc. of 9th Intl. Workshop on News Recommendation and Analytics (RecSys)."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1177\/2053951720943234"},{"key":"e_1_3_2_2_11_1","volume-title":"Conf. on World Wide Web. 880--881","author":"Gulli Antonio","year":"2005","unstructured":"Antonio Gulli. 2005. The anatomy of a news search engine. In Special interest tracks and posters of the 14th Intl. Conf. on World Wide Web. 880--881."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1080\/14241277.2014.997383"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242592"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366424.3382731"},{"key":"e_1_3_2_2_15_1","volume-title":"16th Intl. Conf., CICLing.","author":"Patil S.","unstructured":"S. Patil and B. Ravindran. 2015. Active learning based weak supervision for textual survey response classification. In 16th Intl. Conf., CICLing."},{"key":"e_1_3_2_2_16_1","volume-title":"Empirical Software Engg","volume":"25","author":"Patil S.","year":"2020","unstructured":"S. Patil and B. Ravindran. 2020. Predicting software defect type using concept-based classification. Empirical Software Engg, Vol. 25, 2 (2020)."},{"key":"e_1_3_2_2_17_1","volume-title":"Proc. of the 12th Language Resources and Evaluation Conference.","author":"Rodier Simon","year":"2020","unstructured":"Simon Rodier and Dave Carter. 2020. Online near-duplicate detection of news articles. In Proc. of the 12th Language Resources and Evaluation Conference."},{"key":"e_1_3_2_2_18_1","volume-title":"Proc. of 31st ACM SIGIR.","author":"Theobald M.","unstructured":"M. Theobald, J. Siddharth, and A. Paepcke. 2008. Spotsigs: robust and efficient near duplicate detection in large web collections. In Proc. of 31st ACM SIGIR."},{"key":"e_1_3_2_2_19_1","volume-title":"Syndication: The emerging model for business in the Internet era. Harvard business review","author":"Werbach Kevin","year":"2000","unstructured":"Kevin Werbach. 2000. Syndication: The emerging model for business in the Internet era. Harvard business review, Vol. 78, 3 (2000), 85--85."}],"event":{"name":"WWW '25: The ACM Web Conference 2025","location":"Sydney NSW Australia","acronym":"WWW '25","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Companion Proceedings of the ACM on Web Conference 2025"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3701716.3715303","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T18:26:00Z","timestamp":1759861560000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3701716.3715303"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,8]]},"references-count":19,"alternative-id":["10.1145\/3701716.3715303","10.1145\/3701716"],"URL":"https:\/\/doi.org\/10.1145\/3701716.3715303","relation":{},"subject":[],"published":{"date-parts":[[2025,5,8]]},"assertion":[{"value":"2025-05-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}