{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T18:04:28Z","timestamp":1779991468252,"version":"3.53.1"},"publisher-location":"New York, NY, USA","reference-count":10,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,29]]},"DOI":"10.1145\/3774905.3793116","type":"proceedings-article","created":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T17:14:56Z","timestamp":1779988496000},"page":"120-123","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep Research Comparator: A Platform For Fine-grained Human Annotations of Deep Research Agents"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-5229-6808","authenticated-orcid":false,"given":"Prahaladh","family":"Chandrahasan","sequence":"first","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3309-5642","authenticated-orcid":false,"given":"Jiahe","family":"Jin","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0451-7291","authenticated-orcid":false,"given":"Zhihan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0334-5941","authenticated-orcid":false,"given":"Tevin","family":"Wang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7586-9224","authenticated-orcid":false,"given":"Andy","family":"Tang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5199-9421","authenticated-orcid":false,"given":"Lucy","family":"Mo","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7022-0845","authenticated-orcid":false,"given":"Morteza","family":"Ziyadi","sequence":"additional","affiliation":[{"name":"Amazon, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2639-942X","authenticated-orcid":false,"given":"Leonardo","family":"F.R. Ribeiro","sequence":"additional","affiliation":[{"name":"Amazon, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2258-0304","authenticated-orcid":false,"given":"Zimeng","family":"Qiu","sequence":"additional","affiliation":[{"name":"Amazon, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1117-1070","authenticated-orcid":false,"given":"Markus","family":"Dreyer","sequence":"additional","affiliation":[{"name":"Amazon, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3244-6598","authenticated-orcid":false,"given":"Akari","family":"Asai","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0392-4183","authenticated-orcid":false,"given":"Chenyan","family":"Xiong","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,5,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.2307\/2334029"},{"key":"e_1_3_2_1_2_1","volume-title":"Forty-first International Conference on Machine Learning.","author":"Chiang Wei-Lin","year":"2024","unstructured":"Wei-Lin Chiang, Lianmin Zheng, Ying Sheng, Anastasios Nikolas Angelopoulos, Tianle Li, Dacheng Li, Banghua Zhu, Hao Zhang, Michael Jordan, Joseph E Gonzalez, et al., 2024. Chatbot arena: An open platform for evaluating llms by human preference. In Forty-first International Conference on Machine Learning."},{"key":"e_1_3_2_1_3_1","unstructured":"Jo\u00e3o Coelho Jingjie Ning Jingyuan He Kangrui Mao Abhijay Paladugu Pranav Setlur Jiahe Jin Jamie Callan Jo\u00e3o Magalh\u00e3es Bruno Martins and Chenyan Xiong. 2025. DeepResearchGym: A Free Transparent and Reproducible Evaluation Sandbox for Deep Research. arXiv:2505.19253 [cs.IR] https:\/\/arxiv.org\/abs\/2505.19253"},{"key":"e_1_3_2_1_4_1","volume-title":"DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents. arXiv preprint arXiv:2506.11763","author":"Du Mingxuan","year":"2025","unstructured":"Mingxuan Du, Benfeng Xu, Chiwei Zhu, Xiaorui Wang, and Zhendong Mao. 2025. DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents. arXiv preprint arXiv:2506.11763 (2025)."},{"key":"e_1_3_2_1_5_1","unstructured":"Boyu Gou Zanming Huang Yuting Ning Yu Gu Michael Lin Weijian Qi Andrei Kopanev Botao Yu Bernal Jim\u00e9nez Guti\u00e9rrez Yiheng Shu Chan Hee Song Jiaman Wu Shijie Chen Hanane Nour Moussa Tianshu Zhang Jian Xie Yifei Li Tianci Xue Zeyi Liao Kai Zhang Boyuan Zheng Zhaowei Cai Viktor Rozgic Morteza Ziyadi Huan Sun and Yu Su. 2025. Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge. arXiv:2506.21506 [cs.AI] https:\/\/arxiv.org\/abs\/2506.21506"},{"key":"e_1_3_2_1_6_1","unstructured":"GPTResearcher. 2025. Say Goodbye to Hours of Research. https:\/\/gptr.dev\/"},{"key":"e_1_3_2_1_7_1","unstructured":"Xiaoxi Li Jiajie Jin Guanting Dong Hongjin Qian Yutao Zhu Yongkang Wu Ji-Rong Wen and Zhicheng Dou. 2025. WebThinker: Empowering Large Reasoning Models with Deep Research Capability. arXiv:2504.21776 [cs.CL] https:\/\/arxiv.org\/abs\/2504.21776"},{"key":"e_1_3_2_1_8_1","unstructured":"Gr\u00e9goire Mialon Cl\u00e9mentine Fourrier Craig Swift Thomas Wolf Yann LeCun and Thomas Scialom. 2023. GAIA: a benchmark for General AI Assistants. arXiv:2311.12983 [cs.CL] https:\/\/arxiv.org\/abs\/2311.12983"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3536321"},{"key":"e_1_3_2_1_10_1","volume-title":"Alex Tachard Passos, William Fedus, and Amelia Glaese.","author":"Wei Jason","year":"2025","unstructured":"Jason Wei, Zhiqing Sun, Spencer Papay, Scott McKinney, Jeffrey Han, Isa Fulford, Hyung Won Chung, Alex Tachard Passos, William Fedus, and Amelia Glaese. 2025. BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents. arXiv:2504.12516 [cs.CL] https:\/\/arxiv.org\/abs\/2504.12516"}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Companion Proceedings of the ACM Web Conference 2026"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774905.3793116","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T17:23:57Z","timestamp":1779989037000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774905.3793116"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,28]]},"references-count":10,"alternative-id":["10.1145\/3774905.3793116","10.1145\/3774905"],"URL":"https:\/\/doi.org\/10.1145\/3774905.3793116","relation":{},"subject":[],"published":{"date-parts":[[2026,5,28]]},"assertion":[{"value":"2026-05-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}