{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:46:58Z","timestamp":1783738018180,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,18]]},"DOI":"10.1145\/3731120.3744597","type":"proceedings-article","created":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T13:34:06Z","timestamp":1752845646000},"page":"307-314","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Neural Prioritisation for Web Crawling"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-2364-2043","authenticated-orcid":false,"given":"Francesca","family":"Pezzuti","sequence":"first","affiliation":[{"name":"University of Pisa, Pisa, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8914-2659","authenticated-orcid":false,"given":"Sean","family":"MacAvaney","sequence":"additional","affiliation":[{"name":"University of Glasgow, Glasgow, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7427-1001","authenticated-orcid":false,"given":"Nicola","family":"Tonellotto","sequence":"additional","affiliation":[{"name":"University of Pisa, Pisa, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,7,18]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"117","article-title":"Web Structure","author":"Baeza-Yates Ricardo","year":"2002","unstructured":"Ricardo Baeza-Yates, Felipe Saint-Jean, and Carlos Castillo. 2002. ''Web Structure, Dynamics and Page Quality''. In Proc. SPIRE. 117-132.","journal-title":"Dynamics and Page Quality''. In Proc. SPIRE."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1052934.1052938"},{"key":"e_1_3_2_1_3_1","first-page":"168","article-title":"Do Your Worst to Make the Best","author":"Boldi Paolo","year":"2004","unstructured":"Paolo Boldi, Massimo Santini, and Sebastiano Vigna. 2004. Do Your Worst to Make the Best: Paradoxical Effects in PageRank Incremental Computations. In Proc. WAW. 168-180.","journal-title":"Paradoxical Effects in PageRank Incremental Computations. In Proc. WAW."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1389-1286(99)00052-3"},{"key":"e_1_3_2_1_5_1","first-page":"174","article-title":"Neural Passage Quality Estimation for Static Pruning","author":"Chang Xuejun","year":"2024","unstructured":"Xuejun Chang, Debabrata Mishra, Craig Macdonald, and Sean MacAvaney. 2024. Neural Passage Quality Estimation for Static Pruning. In Proc. SIGIR. 174-185.","journal-title":"Proc. SIGIR."},{"key":"e_1_3_2_1_6_1","first-page":"743","article-title":"Towards a Better Understanding of Query Reformulation Behavior in Web Search","author":"Chen Jia","year":"2021","unstructured":"Jia Chen, Jiaxin Mao, Yiqun Liu, Fan Zhang, Min Zhang, and Shaoping Ma. 2021. Towards a Better Understanding of Query Reformulation Behavior in Web Search. In Proc. WWW. 743-755.","journal-title":"Proc. WWW."},{"key":"e_1_3_2_1_7_1","volume-title":"Harsha Vardhan Simhadri, Manik Varma, Yujing Wang, Linjun Yang, Mao Yang, and Ce Zhang.","author":"Chen Qi","year":"2024","unstructured":"Qi Chen, Xiubo Geng, Corby Rosset, Carolyn Buractaon, Jingwen Lu, Tao Shen, Kun Zhou, Chenyan Xiong, Yeyun Gong, Paul Bennett, Nick Craswell, Xing Xie, Fan Yang, Bryan Tower, Nikhil Rao, Anlei Dong, Wenqi Jiang, Zheng Liu, Mingqin Li, Chuanjie Liu, Zengzhong Li, Rangan Majumder, Jennifer Neville, Andy Oakley, Knut Magne Risvik, Harsha Vardhan Simhadri, Manik Varma, Yujing Wang, Linjun Yang, Mao Yang, and Ce Zhang. 2024. MS MARCO Web Search: A Large-scale Information-rich Web Dataset with Millions of Real Click Labels. In Proc. WWW. 292-301."},{"key":"e_1_3_2_1_8_1","first-page":"1","article-title":"Efficient crawling through URL ordering","volume":"30","author":"Cho Junghoo","year":"1998","unstructured":"Junghoo Cho, Hector Garcia-Molina, and Lawrence Page. 1998. Efficient crawling through URL ordering. Computer Networks, Vol. 30, 1-7 (1998), 161-172.","journal-title":"Computer Networks"},{"key":"e_1_3_2_1_9_1","volume-title":"Manning","author":"Clark Kevin","year":"2020","unstructured":"Kevin Clark, Minh-Thang Luong, Quoc V. Le, and Christopher D. Manning. 2020. ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators. In Proc. ICLR."},{"key":"e_1_3_2_1_10_1","first-page":"183","article-title":"Information retrieval in the World-Wide Web: Making client-based searching feasible","volume":"27","author":"De Bra Paul M.E.","year":"1994","unstructured":"Paul M.E. De Bra and Reinier D.J. Post. 1994. Information retrieval in the World-Wide Web: Making client-based searching feasible. Computer Networks, Vol. 27, 2 (1994), 183-192.","journal-title":"Computer Networks"},{"key":"e_1_3_2_1_11_1","first-page":"1174","article-title":"Ontology-focused crawling of Web documents","author":"Ehrig Marc","year":"2003","unstructured":"Marc Ehrig and Alexander Maedche. 2003. Ontology-focused crawling of Web documents. In Proc. SAC. 1174-1178.","journal-title":"Proc. SAC."},{"key":"e_1_3_2_1_12_1","first-page":"1","article-title":"Leveraging temporal dynamics of document content in relevance ranking","author":"Elsas Jonathan L.","year":"2010","unstructured":"Jonathan L. Elsas and Susan T. Dumais. 2010. Leveraging temporal dynamics of document content in relevance ranking. In Proc. WSDM. 1-10.","journal-title":"Proc. WSDM."},{"key":"e_1_3_2_1_13_1","first-page":"388","article-title":"Measuring the Search Effectiveness of a Breadth-First Crawl","author":"Fetterly Dennis","year":"2009","unstructured":"Dennis Fetterly, Nick Craswell, and Vishwa Vinay. 2009a. Measuring the Search Effectiveness of a Breadth-First Crawl. In Proc. ECIR. 388-399.","journal-title":"Proc. ECIR."},{"key":"e_1_3_2_1_14_1","first-page":"580","article-title":"The impact of crawl policy on web search effectiveness","author":"Fetterly Dennis","year":"2009","unstructured":"Dennis Fetterly, Nick Craswell, and Vishwa Vinay. 2009b. The impact of crawl policy on web search effectiveness. In Proc. SIGIR. 580-587.","journal-title":"Proc. SIGIR."},{"key":"e_1_3_2_1_15_1","first-page":"35","article-title":"Searching by Talking","author":"Guy Ido","year":"2016","unstructured":"Ido Guy. 2016. Searching by Talking: Analysis of Voice Queries on Mobile Web Search. In Proc. SIGIR. 35-44.","journal-title":"Analysis of Voice Queries on Mobile Web Search. In Proc. SIGIR."},{"key":"e_1_3_2_1_16_1","volume-title":"Applied Network Science","volume":"4","author":"Helge Holzmann","year":"2019","unstructured":"Holzmann Helge, Anand Avishek, and Khosla Megha. 2019. Estimating PageRank deviations in crawled graphs. Applied Network Science, Vol. 4, 86 (2019)."},{"key":"e_1_3_2_1_17_1","first-page":"1","article-title":"The shark-search algorithm. An application: tailored Web site mapping","volume":"30","author":"Hersovici Michael","year":"1998","unstructured":"Michael Hersovici, Michal Jacovi, Yoelle S. Maarek, Dan Pelleg, Menachem Shtalhaim, and Sigalit Ur. 1998. The shark-search algorithm. An application: tailored Web site mapping. Computer Networks, Vol. 30, 1-7 (1998), 317-326.","journal-title":"Computer Networks"},{"key":"e_1_3_2_1_18_1","first-page":"495","article-title":"Optimal Freshness Crawl Under Politeness Constraints","author":"Kolobov Andrey","year":"2019","unstructured":"Andrey Kolobov, Yuval Peres, Eyal Lubetzky, and Eric Horvitz. 2019. Optimal Freshness Crawl Under Politeness Constraints. In Proc. SIGIR. 495-504.","journal-title":"Proc. SIGIR."},{"key":"e_1_3_2_1_19_1","volume-title":"Web Searching: A Quality Measurement Perspective","author":"Lewandowski Dirk","year":"2008","unstructured":"Dirk Lewandowski and Nadine H\u00f6chst\u00f6tter. 2008. Web Searching: A Quality Measurement Perspective. Springer, 309-340."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009953814988"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1031114.1031117"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/383952.383995"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/371920.371965"},{"key":"e_1_3_2_1_24_1","first-page":"437","article-title":"Recrawl scheduling based on information longevity","author":"Olston Christopher","year":"2008","unstructured":"Christopher Olston and Sandeep Pandey. 2008. Recrawl scheduling based on information longevity. In Proc. WWW. 437-446.","journal-title":"Proc. WWW."},{"key":"e_1_3_2_1_25_1","first-page":"100","article-title":"Crawling Policies Based on Web Page Popularity Prediction","author":"Ostroumova Liudmila","year":"2014","unstructured":"Liudmila Ostroumova, Ivan Bogatyy, Arseniy Chelnokov, Alexey Tikhonov, and Gleb Gusev. 2014. Crawling Policies Based on Web Page Popularity Prediction. In Proc. ECIR. 100-111.","journal-title":"Proc. ECIR."},{"key":"e_1_3_2_1_26_1","first-page":"3360","article-title":"ClueWeb22: 10 Billion Web Documents with Rich Information","author":"Overwijk Arnold","year":"2022","unstructured":"Arnold Overwijk, Chenyan Xiong, and Jamie Callan. 2022. ClueWeb22: 10 Billion Web Documents with Rich Information. In Proc. SIGIR. 3360-3362.","journal-title":"Proc. SIGIR."},{"key":"e_1_3_2_1_27_1","volume-title":"Proc. WWW.","author":"Page Lawrence","year":"1999","unstructured":"Lawrence Page, Sergey Brin, Rajeev Motwani, and Terry Winograd. 1999. The PageRank Citation Ranking: Bringing Order to the Web. In Proc. WWW."},{"key":"e_1_3_2_1_28_1","first-page":"781","article-title":"Shuffling a Stacked Deck","author":"Pandey Sandeep","year":"2005","unstructured":"Sandeep Pandey, Sourashis Roy, Christopher Olston, Junghoo Cho, and Soumen Chakrabarti. 2005. Shuffling a Stacked Deck: The Case for Partially Randomized Ranking of Search Engine Results. In Proc. VLDB. 781-792.","journal-title":"In Proc. VLDB."},{"key":"e_1_3_2_1_29_1","first-page":"221","article-title":"Search Engine-Crawler Symbiosis: Adapting to Community Interests","author":"Pant Gautam","year":"2003","unstructured":"Gautam Pant, Shannon Bradshaw, and Filippo Menczer. 2003. Search Engine-Crawler Symbiosis: Adapting to Community Interests. In Proc. TPDL. 221-232.","journal-title":"Proc. TPDL."},{"key":"e_1_3_2_1_30_1","first-page":"107","article-title":"Link contexts in classifier-guided topical crawlers","volume":"18","author":"Pant Gautam","year":"2006","unstructured":"Gautam Pant and Padmini Srinivasan. 2006. Link contexts in classifier-guided topical crawlers. IEEE TKDE, Vol. 18, 1 (2006), 107-122.","journal-title":"IEEE TKDE"},{"key":"e_1_3_2_1_31_1","unstructured":"Francesca Pezzuti Ariane Mueller Sean MacAvaney and Nicola Tonellotto. 2025. Document Quality Scoring for Web Crawling. (2025). arXiv:2504.11011."},{"key":"e_1_3_2_1_32_1","volume-title":"Researchy Questions: A Dataset of Multi-Perspective, Decompositional Questions for LLM Web Agents.","author":"Rosset Corby","year":"2024","unstructured":"Corby Rosset, Ho-Lam Chung, Guanghui Qin, Ethan C. Chau, Zhuo Feng, Ahmed Awadallah, Jennifer Neville, and Nikhil Rao. 2024. Researchy Questions: A Dataset of Multi-Perspective, Decompositional Questions for LLM Web Agents. (2024). arXiv:2402.17896."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/361219.361220"},{"key":"e_1_3_2_1_34_1","first-page":"1785","article-title":"On the Role of Relevance in Natural Language Processing Tasks","author":"Sauchuk Artsiom","year":"2022","unstructured":"Artsiom Sauchuk, James Thorne, Alon Y. Halevy, Nicola Tonellotto, and Fabrizio Silvestri. 2022. On the Role of Relevance in Natural Language Processing Tasks. In Proc. SIGIR. 1785-1789.","journal-title":"Proc. SIGIR."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-024-18559-4"},{"key":"e_1_3_2_1_36_1","first-page":"2703","article-title":"What do Users Really Ask Large Language Models","author":"Trippas Johanne R.","year":"2024","unstructured":"Johanne R. Trippas, Sara Fahad Dawood Al Lawati, Joel Mackenzie, and Luke Gallagher. 2024. What do Users Really Ask Large Language Models? An Initial Log Analysis of Google Bard Interactions in the Wild. In Proc. SIGIR. 2703-2707.","journal-title":"In Proc. SIGIR."},{"key":"e_1_3_2_1_37_1","first-page":"1","article-title":"A New Era of Web Mining","author":"Tyagi Lalit Kumar","year":"2023","unstructured":"Lalit Kumar Tyagi, Anish Gupta, and Vibhash Singh Sisodia. 2023. A New Era of Web Mining: Innovative Approaches in Focused Web Crawling for Domain-Specific Information. In Proc. ICTACS. 1-6.","journal-title":"In Proc. ICTACS."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3655615"},{"key":"e_1_3_2_1_39_1","first-page":"3892","article-title":"A Prompt Log Analysis of Text-to-Image Generation Systems","author":"Xie Yutong","year":"2023","unstructured":"Yutong Xie, Zhaoying Pan, Jinge Ma, Luo Jie, and Qiaozhu Mei. 2023. A Prompt Log Analysis of Text-to-Image Generation Systems. In Proc. WWW. 3892-3902.","journal-title":"Proc. WWW."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Shi Yu Zhiyuan Liu and Chenyan Xiong. 2025. Craw4LLM: Efficient Web Crawling for LLM Pretraining. (2025). arXiv:2502.13347.","DOI":"10.18653\/v1\/2025.findings-acl.712"}],"event":{"name":"ICTIR '25: International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval","location":"Padua Italy","acronym":"ICTIR '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 2025 International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR)"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731120.3744597","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T13:17:20Z","timestamp":1755868640000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731120.3744597"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,18]]},"references-count":40,"alternative-id":["10.1145\/3731120.3744597","10.1145\/3731120"],"URL":"https:\/\/doi.org\/10.1145\/3731120.3744597","relation":{},"subject":[],"published":{"date-parts":[[2025,7,18]]},"assertion":[{"value":"2025-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}