{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T13:30:21Z","timestamp":1767706221766,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,7,11]],"date-time":"2021-07-11T00:00:00Z","timestamp":1625961600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,7,11]]},"DOI":"10.1145\/3404835.3463251","type":"proceedings-article","created":{"date-parts":[[2021,7,12]],"date-time":"2021-07-12T02:41:52Z","timestamp":1626057712000},"page":"2485-2490","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Seer-Dock: A General-Purpose Dockerized Scholarly Document Collection and Management Framework"],"prefix":"10.1145","author":[{"given":"Dina","family":"Sayed","sequence":"first","affiliation":[{"name":"University of Basel, Basel, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohamed","family":"Nour","sequence":"additional","affiliation":[{"name":"Independent Researcher, Cairo, Egypt"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heiko","family":"Schuldt","sequence":"additional","affiliation":[{"name":"University of Basel, Basel, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,7,11]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"2021. CKAN. https:\/\/ckan.org\/"},{"key":"e_1_3_2_2_2_1","unstructured":"2021. Elasticsearch. https:\/\/www.elastic.co\/elasticsearch\/"},{"key":"e_1_3_2_2_3_1","unstructured":"2021. Zenodo. https:\/\/about.zenodo.org\/infrastructure\/"},{"key":"e_1_3_2_2_4_1","volume-title":"Invenio: A modern digital library for grey literature.","author":"Caffaro Jerome","year":"2010","unstructured":"Jerome Caffaro and Samuele Kaplun. 2010. Invenio: A modern digital library for grey literature."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1045\/march1007-castelli"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1031453.1031454"},{"key":"e_1_3_2_2_7_1","volume-title":"Retrieved","author":"Giles Clyde Lee","year":"2015","unstructured":"Clyde Lee Giles. 2015. CiteSeerX related publications. Retrieved February 20, 2021 from https:\/\/clgiles.ist.psu.edu\/citeseer-related.pdf"},{"key":"e_1_3_2_2_8_1","volume-title":"Retrieved","author":"Giles Clyde Lee","year":"2015","unstructured":"Clyde Lee Giles. 2015. CiteSeerX Team. Retrieved February 20, 2021 fromhttps:\/\/csxstatic.ist.psu.edu\/people\/team"},{"key":"e_1_3_2_2_9_1","unstructured":"Clyde Lee Giles Kurt Bollacker and Steve Lawrence. 2008. CiteSeerX. Retrieved February 5 2021 from https:\/\/csxstatic.ist.psu.edu\/home"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1135777.1135926"},{"key":"e_1_3_2_2_11_1","volume-title":"MeiliSearch - Github source code.https:\/\/github.com\/meilisearch\/MeiliSearch [Online","author":"MeiliSearch","year":"2021","unstructured":"MeiliSearch 2021. MeiliSearch - Github source code.https:\/\/github.com\/meilisearch\/MeiliSearch [Online; accessed 20-February-2021]."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1317353.1317356"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1300\/J141v01n02_04"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-45442-5_60"},{"volume-title":"Penn State University","author":"Qingzhao Tan","key":"e_1_3_2_2_15_1","unstructured":"Tan Qingzhao. 2008.Designing new crawling and indexing techniques for web search engines. Ph.D. Dissertation. Penn State University, State College, PA 16801, USA. Advisor(s) Mitra Prasenjit."},{"key":"e_1_3_2_2_16_1","volume-title":"Proceedings of the ACM Symposium on Document Engineering. 1--4.","author":"Rohatgi Shaurya","year":"2020","unstructured":"Shaurya Rohatgi, Zeba Karishma, Jason Chhay, Sai Raghav Reddy Keesara, Jian Wu, Cornelia Caragea, and Clyde Lee Giles. 2020. COVID Seer: Extending the CORD-19 Dataset. In Proceedings of the ACM Symposium on Document Engineering. 1--4."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"crossref","unstructured":"MacKenzie Smith Mary Barton Mick Bass Margret Branschofsky Greg McClellan Dave Stuve Robert Tansley and Julie Harford Walker. 2003. DSpace: An open source dynamic digital repository. (2003).","DOI":"10.1045\/january2003-smith"},{"key":"e_1_3_2_2_18_1","volume-title":"Privacy at scale: Introducing the privaseer corpus of web privacy policies. arXiv preprintarXiv","author":"Srinath Mukund","year":"2004","unstructured":"Mukund Srinath, Wilson, Shomir, and Clyde Lee Giles. 2020. Privacy at scale: Introducing the privaseer corpus of web privacy policies. arXiv preprintarXiv: 2004.11131(2020)."},{"key":"e_1_3_2_2_19_1","unstructured":"Robert Tansley. 2000. Eprints.org software for creating institutional and individual open archives. D-Lib Magazine(2000)."},{"key":"e_1_3_2_2_20_1","volume-title":"Typesense - Github source code. https:\/\/github.com\/typesense\/typesense [Online","author":"Typesense","year":"2021","unstructured":"Typesense 2021. Typesense - Github source code. https:\/\/github.com\/typesense\/typesense [Online; accessed 20-February-2021]."},{"key":"e_1_3_2_2_21_1","unstructured":"Jian Wu Douglas Jordan Kyle Williams Pradeep Teregowda Stephen Carman and Po-Yu Chuang. 2015. CiteSeerX Manual (CXM). Retrieved February 3 2021from https:\/\/github.com\/SeerLabs\/CiteSeerX\/blob\/master\/doc\/cxm.pdf"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3359115.3359119"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v36i3.2601"}],"event":{"name":"SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Virtual Event Canada","acronym":"SIGIR '21"},"container-title":["Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404835.3463251","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3404835.3463251","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:17:44Z","timestamp":1750191464000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404835.3463251"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,11]]},"references-count":23,"alternative-id":["10.1145\/3404835.3463251","10.1145\/3404835"],"URL":"https:\/\/doi.org\/10.1145\/3404835.3463251","relation":{},"subject":[],"published":{"date-parts":[[2021,7,11]]},"assertion":[{"value":"2021-07-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}