DesignationISO/IEC FDIS 24029-3

Stage50.00, FDIS registered

Planning date, an estimate16 Feb 2027

Text todayPublic record and DIS view

Home / The methods the draft points to

The methods the draft points to

The bibliography, grouped by the method family it names, and how each family sits beside formal methods.

7 pages in this group. Every page states its citation, the evidence a reviewer asks for, and what it does not cover. Last updated: 2026-10-21.

Behavioural testing, CheckList

The draft's bibliography cites a task-agnostic behavioural testing method for NLP models. The cited work argues that held-out accuracy can overestimate performance and proposes a matrix of c

Bibliography [7]: Ribeiro, Wu, Guestrin and Singh, Beyond accuracy: Behavioral testing of NLP models with CheckList (2020)

Statistical reachability analysis

The bibliography cites a reachability method presented at ESEC/FSE in 2023. Reachability asks whether a set of states can be reached, and the statistical version samples rather than enumerat

Bibliography [8]: Lee and Boehme, Statistical Reachability Analysis (ESEC/FSE 2023)

Adversarial examples and data concentration

The bibliography cites a paper on how the concentration of data affects adversarial robustness. Its title asks whether adversarial examples can be avoided, which puts the data distribution a

Bibliography [9]: Pal, Sulam and Vidal, Adversarial examples might be avoidable: the role of data concentration in adversarial robustness (2023)

Corruption robustness and its efficient assessment

The bibliography cites two works on corruption robustness: an evaluation framework and an efficient statistical assessment method. Both concern performance under input corruptions rather tha

Bibliography [10] and [11]: SMART, a robustness evaluation framework for neural networks (2022); Tit, Furon and Rousset, Efficient statistical assessment of neural network corruption robustness (2021)

A statistical approach to robustness

The bibliography cites a paper that treats robustness as a statistical estimate. The cited work frames the result as an estimate over an input distribution, not only as a worst case.

Bibliography [12]: Webb, Rainforth, Teh and Kumar, A statistical approach to assessing neural network robustness (2019)

Uncertainty, complexity and model confidence

The bibliography cites a theory of AI uncertainty built on Rademacher complexity and Shannon entropy, and the dropout-as-Bayesian-approximation method for representing model uncertainty in d

Bibliography [13] and [14]: Zhou, A theory on AI uncertainty based on Rademacher complexity and Shannon entropy (2020); Gal and Ghahramani, Dropout as a Bayesian approximation (2016)

Manifold analysis and the stability of cross-validation

The bibliography cites a manifold-based robustness analysis and a theory of cross-validation through stability. Both concern the geometry of the input space and the reliability of the estima

Bibliography [15] and [18]: Sekmen and Bilgin, Manifold-based approach for neural network robustness analysis (2024); Lei, A modern theory of cross-validation through the lens of stability (2025)