{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T18:05:25Z","timestamp":1779991525310,"version":"3.53.1"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,29]]},"DOI":"10.1145\/3774905.3795485","type":"proceedings-article","created":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T17:14:56Z","timestamp":1779988496000},"page":"989-998","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Automating Computational Reproducibility in Social Science: Comparing Prompt-Based and Agent-Based Approaches"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-8199-1451","authenticated-orcid":false,"given":"Syed Mehtab Hussain","family":"Shah","sequence":"first","affiliation":[{"name":"GESIS - Leibniz-Institut f\u00fcr Sozialwissenschaften, Cologne, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0380-6088","authenticated-orcid":false,"given":"Frank","family":"Hopfgartner","sequence":"additional","affiliation":[{"name":"University of Koblenz, Koblenz, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3794-0904","authenticated-orcid":false,"given":"Arnim","family":"Bleier","sequence":"additional","affiliation":[{"name":"GESIS - Leibniz-Institut f\u00fcr Sozialwissenschaften, Cologne, Germany"}],"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":"10.1038\/533452a"},{"key":"e_1_3_2_1_2_1","volume-title":"Terminologies for Reproducible Research. arXiv preprint arXiv:1802.03311","author":"Barba Lorena A.","year":"2018","unstructured":"Lorena A. Barba. 2018. Terminologies for Reproducible Research. arXiv preprint arXiv:1802.03311 (2018). https:\/\/arxiv.org\/abs\/1802.03311"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Carl Boettiger and Dirk Eddelbuettel. 2017. An Introduction to Rocker: Docker Containers for R. arXiv:1710.03675 [cs.SE] https:\/\/arxiv.org\/abs\/1710.03675","DOI":"10.32614\/RJ-2017-065"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2899401"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.5117\/CCR2024.1.5.CHAN"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1190\/1.1822162"},{"key":"e_1_3_2_1_7_1","unstructured":"L\u00e1zaro Costa Susana Barbosa and J\u00e1come Cunha. 2025. A Dataset For Computational Reproducibility. arXiv:2504.08684 [cs.SE] https:\/\/arxiv.org\/abs\/2504.08684"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Andor Diera Abdelhalim Dahou Lukas Galke Fabian Karl Florian Sihler and Ansgar Scherp. 2023. GenCodeSearchNet: A Benchmark Test Suite for Evaluating Generalization in Programming Language Understanding. arXiv:2311.09707 [cs.CL] https:\/\/arxiv.org\/abs\/2311.09707","DOI":"10.18653\/v1\/2023.genbench-1.2"},{"key":"e_1_3_2_1_9_1","unstructured":"Yufeng Du Minyang Tian Srikanth Ronanki Subendhu Rongali Sravan Bodapati Aram Galstyan Azton Wells Roy Schwartz Eliu A Huerta and Hao Peng. 2025. Context Length Alone Hurts LLM Performance Despite Perfect Retrieval. arXiv:2510.05381 [cs.CL] https:\/\/arxiv.org\/abs\/2510.05381"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1098\/rsos.180448"},{"key":"e_1_3_2_1_11_1","volume-title":"Austin Peters, and Daniel Kang","author":"Hu Chuxuan","year":"2025","unstructured":"Chuxuan Hu, Liyun Zhang, Yeji Lim, Aum Wadhwani, Austin Peters, and Daniel Kang. 2025. REPRO-Bench: Can Agentic AI Systems Assess the Reproducibility of Social Science Research? arXiv:2507.18901 [cs.CL] https:\/\/arxiv.org\/abs\/2507.18901"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0300333"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.17226\/25303"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41669-024-00476-9"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/tse.2025.3541166"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.36190\/2025.49"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1140\/epjds\/s13688-024-00514-w"},{"key":"e_1_3_2_1_19_1","unstructured":"Zachary S. Siegel Sayash Kapoor Nitya Nagdir Benedikt Stroebl and Arvind Narayanan. 2024. CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmark. arXiv:2409.11363 [cs.CL] https:\/\/arxiv.org\/abs\/2409.11363"},{"key":"e_1_3_2_1_20_1","volume-title":"Leon Maksin, Rachel Dias, Evan Mays, Benjamin Kinsella, Wyatt Thompson, Johannes Heidecke, Amelia Glaese, and Tejal Patwardhan.","author":"Starace Giulio","year":"2025","unstructured":"Giulio Starace, Oliver Jaffe, Dane Sherburn, James Aung, Jun Shern Chan, Leon Maksin, Rachel Dias, Evan Mays, Benjamin Kinsella, Wyatt Thompson, Johannes Heidecke, Amelia Glaese, and Tejal Patwardhan. 2025. PaperBench: Evaluating AI's Ability to Replicate AI Research. arXiv:2504.01848 [cs.AI] https:\/\/arxiv.org\/abs\/2504.01848"},{"key":"e_1_3_2_1_21_1","volume-title":"Sicheng Zhong, Wei-Long Zheng, Xujie Si, and Kevin Ellis.","author":"Tang Hao","year":"2024","unstructured":"Hao Tang, Keya Hu, Jin Peng Zhou, Sicheng Zhong, Wei-Long Zheng, Xujie Si, and Kevin Ellis. 2024. Code Repair with LLMs gives an Exploration-Exploitation Tradeoff. arXiv:2405.17503 [cs.SE] https:\/\/arxiv.org\/abs\/2405.17503"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01143-6"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2024.104724"},{"key":"e_1_3_2_1_24_1","volume-title":"COAST: Enhancing the Code Debugging Ability of LLMs through Communicative Agent Based Data Synthesis. arXiv:2408.05006 [cs.SE] https:\/\/arxiv.org\/abs\/2408.05006","author":"Yang Weiqing","year":"2025","unstructured":"Weiqing Yang, Hanbin Wang, Zhenghao Liu, Xinze Li, Yukun Yan, Shuo Wang, Yu Gu, Minghe Yu, Zhiyuan Liu, and Ge Yu. 2025. COAST: Enhancing the Code Debugging Ability of LLMs through Communicative Agent Based Data Synthesis. arXiv:2408.05006 [cs.SE] https:\/\/arxiv.org\/abs\/2408.05006"},{"key":"e_1_3_2_1_25_1","unstructured":"Alex L. Zhang Tim Kraska and Omar Khattab. 2025b. Recursive Language Models. arXiv:2512.24601 [cs.AI] https:\/\/arxiv.org\/abs\/2512.24601"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1038\/s44387-025-00019-510.1038\/s44387-025-"}],"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\/3774905.3795485","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T17:28:38Z","timestamp":1779989318000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774905.3795485"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,28]]},"references-count":26,"alternative-id":["10.1145\/3774905.3795485","10.1145\/3774905"],"URL":"https:\/\/doi.org\/10.1145\/3774905.3795485","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"}}]}}