Preprint · 2016 · Open access

Towards Verified Artificial Intelligence

Sanjit Arunkumar Seshia, Dorsa Sadigh, Shankar Sastry

arXiv (Cornell University) · Published 27 June 2016 · DOI 10.48550/arxiv.1606.08514

Open PDFView at the publisherCite this paper

In brief

“Towards Verified Artificial Intelligence” is a 2016 preprint by Sanjit Arunkumar Seshia and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 198 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
198
Most cited in
2019 (39)
References
99
Authors
3

Abstract

Verified artificial intelligence (AI) is the goal of designing AI-based systems that that have strong, ideally provable, assurances of correctness with respect to mathematically-specified requirements. This paper considers Verified AI from a formal methods perspective. We describe five challenges for achieving Verified AI, and five corresponding principles for addressing these challenges.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Seshia, S. A., Sadigh, D., & Sastry, S. (2016). Towards Verified Artificial Intelligence. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1606.08514

MLA 9

Seshia, Sanjit Arunkumar, et al. “Towards Verified Artificial Intelligence.” arXiv (Cornell University), 2016. https://doi.org/10.48550/arxiv.1606.08514.

Chicago

Seshia, Sanjit Arunkumar, Dorsa Sadigh, and Shankar Sastry. 2016. “Towards Verified Artificial Intelligence.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.1606.08514.

Harvard

Seshia, S. A., Sadigh, D. and Sastry, S. (2016) ‘Towards Verified Artificial Intelligence’, arXiv (Cornell University). doi:10.48550/arxiv.1606.08514.

IEEE

S. A. Seshia, D. Sadigh, and S. Sastry, “Towards Verified Artificial Intelligence,” arXiv (Cornell University), 2016, doi: 10.48550/arxiv.1606.08514.

BibTeX

@misc{seshia2016towards,
  title     = {{Towards Verified Artificial Intelligence}},
  author    = {Seshia, Sanjit Arunkumar and Sadigh, Dorsa and Sastry, Shankar},
  howpublished = {arXiv (Cornell University)},
  year      = {2016},
  doi       = {10.48550/arxiv.1606.08514},
  url       = {https://doi.org/10.48550/arxiv.1606.08514}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
201755
20182424
20193939
20203737
20212121
20223232
20231717
202499
202577
202666

Topic and keywords

Physical Sciences › Computer Science › Computational Theory and Mathematics › Formal Methods in Verification

  • formal methods
  • AI system design
  • requirements specification

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Seshia, S. A., Sadigh, D., & Sastry, S. (2016). Towards Verified Artificial Intelligence. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1606.08514

How many times has this paper been cited?

198 times, according to OpenAlex on 19 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 arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Sanjit Arunkumar Seshia, Dorsa Sadigh, Shankar Sastry.

What is the DOI of this paper?

10.48550/arxiv.1606.08514, permanently at https://doi.org/10.48550/arxiv.1606.08514. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 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.