Outline: Proposed Zero Draft for a Standard on AI Testing, Evaluation, Verification, and Validation

Authors

  • NIST U.S. Department of Commerce

DOI:

https://doi.org/10.70777/si.v2i5.15513

Keywords:

AI Testing, AI Evaluation, AI Verification, AI Validation, TEVV Framework, AI Governance, AI Standards, AI complexity

Abstract

Background and Purpose

In March 2025, NIST announced its AI Standards Zero Drafts project. In this pilot project, NIST is collecting input on topics with a science-backed body of work and using it to develop “zero drafts”—preliminary, stakeholder-driven drafts of standards that are as thorough as possible. These drafts will then be submitted into the private sector-led standardization process as proposals for voluntary consensus standards. The project aims to broaden participation in and accelerate the creation of standards, helping standards meet the AI community’s needs and unleash AI innovation.

Based on community input, NIST selected two topics for the Zero Drafts pilot, one of which is AI testing, evaluation, verification and validation (TEVV). This detailed outline proposes a direction and structure for the forthcoming zero draft on TEVV. Based on this paper and input received in response, NIST will propose concrete text for a zero draft, which the community will also be invited to provide input on.

The resulting draft will be submitted to INCITS/AI, the private sector-led committee that represents the United States to ISO/IEC JTC 1/SC 42. SC 42 is the subcommittee that focuses on cross-sectoral AI standards development within ISO and IEC (two prominent international standards developing organizations that collaborate closely through joint committees). Assuming that INCITS/AI proposes the draft as a new project for SC 42 and that SC 42 takes up the proposal, the future of the document will be up to the usual consensus processes of standards development. NIST does not expect to maintain the document further, and will have no greater influence over the resulting standard than a typical contributor to an ISO/IEC national body.  

Author Biography

NIST, U.S. Department of Commerce

NIST promotes innovation and cultivates trust in the design, development, use and governance of artificial intelligence (AI) technologies and systems in ways that enhance economic security, competitiveness, and quality of life.

NIST advances a risk-based approach to maximize the benefits of AI while minimizing its potential negative consequences. NIST efforts focus on fundamental research to improve AI measurement science, standards, and related tools — including benchmarks and evaluations. NIST has a nonregulatory measurement science mission that encourages engagement with industry and others who voluntarily adopt its guidance. 

Under the White House Winning the Race: America’s AI Action Plan released on July 23, 2025, NIST is named in a large number of recommended policy actions.

NIST recently launched its AI Standards “Zero Drafts” Pilot Project to accelerate AI innovation by developing AI standards more quickly while encouraging openness and collaboration. Input is encouraged.

Organizational requirements and other factors inform the specific objectives and requirements of an AI evaluation

Downloads

Published

2025-08-11

How to Cite

National Institute of Standards and Technology. (2025). Outline: Proposed Zero Draft for a Standard on AI Testing, Evaluation, Verification, and Validation. SuperIntelligence - Robotics - Safety & Alignment, 2(5). https://doi.org/10.70777/si.v2i5.15513