2606.13670v1 Jun 11, 2026 cs.AI

Automated reproducibility assessments in the social and behavioral sciences using large language models

Frauke Kreuter
Frauke Kreuter
Citations: 383
h-index: 11
S. Feuerriegel
S. Feuerriegel
Citations: 10,075
h-index: 48
Tobias Holtdirk
Tobias Holtdirk
Citations: 3
h-index: 1
Pietro Marcolongo
Pietro Marcolongo
Citations: 0
h-index: 0
Anna Schulten
Anna Schulten
Citations: 137
h-index: 7
Felix Henninger
Felix Henninger
Citations: 8,002
h-index: 14
Stefan Rose
Stefan Rose
Citations: 122
h-index: 4
Sarah Ball
Sarah Ball
Citations: 66
h-index: 4
Bolei Ma
Bolei Ma
Citations: 12
h-index: 2
Markus Weinmann
Markus Weinmann
Citations: 18
h-index: 1

Reproducibility in the social and behavioral sciences is typically evaluated by independent researchers who reanalyze the original data to assess whether the published findings can be recovered. However, such approaches are resource-intensive and difficult to scale. Here, we show that large language models (LLMs) can automate reproducibility assessments. Using N=76 published studies with predefined claims from the behavioral and social sciences, we compare LLM-generated analysis with the original findings and human reanalysis. For 7 studies, the LLM could not produce a viable effect size estimate. For the remaining studies, our LLM pipeline recovered the original effect sizes in 41% of studies using a +/-0.05 tolerance in Cohen's d. Further, our LLM pipeline reached the same qualitative conclusion as the original study in 96% of cases, where conclusions indicate whether the reanalysis supports the original claim. For comparison, human reanalysts recovered the original effect sizes in 34% of studies and reached the same qualitative conclusion in 74% of cases. Together, these results show that LLMs can serve as a scalable tool for automated reproducibility assessment and provide a foundation for systematic auditing of empirical results in the social and behavioral sciences.

0 Citations
0 Influential
24 Altmetric
120.0 Score
Original PDF

No Analysis Report Yet

This paper hasn't been analyzed by Gemini yet.

Log in to request an AI analysis.

댓글

댓글을 작성하려면 로그인하세요.

아직 댓글이 없습니다. 첫 번째 댓글을 남겨보세요!