Journal article · 2025 · Open access
Certificates in AI: Learn but Verify
Communications of the ACM, 69(1), 66–75 · Published 18 December 2025 · DOI 10.1145/3737447
In brief
“Certificates in AI: Learn but Verify” is a 2025 journal article by Clark Barrett and 2 co-authors, published in Communications of the ACM. OpenAlex counts 9 citations as of 18 November 2026, which puts it in the top 2% of works published in 2025 by citations. It is open access under a CC BY licence: the full text is free to read at Communications of the ACM.
- Citations
- 9
- Most cited in
- 2026 (9)
- Field-weighted impact
- 1.47
- References
- 35
- Authors
- 3
Abstract
In certifiable machine learning, AI systems produce not only results but also verifiable certificates that the results can be trusted.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Barrett, C., Henzinger, T. A., & Seshia, S. A. (2025). Certificates in AI: Learn but Verify. Communications of the ACM, 69(1), 66–75. https://doi.org/10.1145/3737447
MLA 9
Barrett, Clark, et al. “Certificates in AI: Learn but Verify.” Communications of the ACM, vol. 69, no. 1, 2025, pp. 66–75. https://doi.org/10.1145/3737447.
Chicago
Barrett, Clark, Thomas A. Henzinger, and Sanjit Arunkumar Seshia. 2025. “Certificates in AI: Learn but Verify.” Communications of the ACM 69 (1): 66–75. https://doi.org/10.1145/3737447.
Harvard
Barrett, C., Henzinger, T. A. and Seshia, S. A. (2025) ‘Certificates in AI: Learn but Verify’, Communications of the ACM, 69(1), pp. 66–75. doi:10.1145/3737447.
IEEE
C. Barrett, T. A. Henzinger, and S. A. Seshia, “Certificates in AI: Learn but Verify,” Communications of the ACM, vol. 69, no. 1, pp. 66–75, 2025, doi: 10.1145/3737447.
BibTeX
@article{barrett2025certificates,
title = {{Certificates in AI: Learn but Verify}},
author = {Barrett, Clark and Henzinger, Thomas A. and Seshia, Sanjit Arunkumar},
journal = {Communications of the ACM},
year = {2025},
volume = {69},
number = {1},
pages = {66--75},
doi = {10.1145/3737447},
url = {https://doi.org/10.1145/3737447}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- verification
- trust in AI
- explainable AI
- formal verification
- AI safety
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Barrett, C., Henzinger, T. A., & Seshia, S. A. (2025). Certificates in AI: Learn but Verify. Communications of the ACM, 69(1), 66–75. https://doi.org/10.1145/3737447
How many times has this paper been cited?
9 times, according to OpenAlex on 18 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at Communications of the ACM: sign in and open the full text from this page.
Who wrote this paper?
Clark Barrett, Thomas A. Henzinger, Sanjit Arunkumar Seshia.
What is the DOI of this paper?
10.1145/3737447, permanently at https://doi.org/10.1145/3737447. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 18 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.