AI-assisted teams outperform AI-led teams but not human-only teams in assessing research reproducibility in quantitative social science

Brodeur, A. orcid.org/0000-0003-3980-4324, Valenta, D. orcid.org/0009-0003-7179-4792, Marcoci, A. orcid.org/0000-0002-5780-0805 et al. (269 more authors) (2026) AI-assisted teams outperform AI-led teams but not human-only teams in assessing research reproducibility in quantitative social science. Proceedings of the National Academy of Sciences, 123 (22). e2524747123. ISSN: 0027-8424

Abstract

Metadata

Item Type: Article
Authors/Creators:
Copyright, Publisher and Additional Information:

© 2026 the Author(s). Published by PNAS. This article is distributed under Creative Commons Attribution-NonCommercial-NoDerivatives License 4.0 (CC BY-NC-ND). https://creativecommons.org/licenses/by-nc-nd/4.0/

Keywords: AI; large language models; reproducibility; Humans; Reproducibility of Results; Large Language Models; Social Sciences; Generative Artificial Intelligence; Artificial Intelligence; Intelligent Systems; Cooperative Behavior
Dates:
  • Submitted: 22 September 2025
  • Accepted: 16 March 2026
  • Published (online): 28 May 2026
  • Published: 2 June 2026
Institution: The University of Sheffield
Academic Units: The University of Sheffield > Faculty of Science (Sheffield) > Department of Psychology (Sheffield)
The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield)
Date Deposited: 09 Jul 2026 10:15
Last Modified: 09 Jul 2026 10:15
Status: Published
Publisher: National Academy of Sciences
Refereed: Yes
Identification Number: 10.1073/pnas.2524747123
Related URLs:
Open Archives Initiative ID (OAI ID):

Export

Statistics