# On Extending the Automatic Test Markup Language (ATML) for Machine Learning

arXiv: https://arxiv.org/abs/2404.03769 · HTML: https://mlsanity.com/paper/2404.03769/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 28 references that are in the map.
- First posted on arXiv 4 Apr 2024.

## Builds on (most cited first, 7 of 7)

- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Adversarial Attacks on Neural Network Policies](https://mlsanity.com/paper/1702.02284/) (2017)
- [A Systems Theory of Transfer Learning](https://mlsanity.com/paper/2107.01196/) (2021)
- [Systematic Training and Testing for Machine Learning Using Combinatorial Interaction Testing](https://mlsanity.com/paper/2201.12428/) (2022)
- [Mesarovician Abstract Learning Systems](https://mlsanity.com/paper/2111.14766/) (2021)
- [Homomorphisms Between Transfer, Multi-Task, and Meta-Learning Systems](https://mlsanity.com/paper/2208.03316/) (2022)
- [Empirically Measuring Transfer Distance for System Design and Operation](https://mlsanity.com/paper/2107.01184/) (2021)

## Built on by (most cited first, 1 of 1)

- [PyMilo: A Python Library for ML I/O](https://mlsanity.com/paper/2501.00528/) (2024)

## Abstract (arXiv)

This paper addresses the urgent need for messaging standards in the operational test and evaluation (T&E) of machine learning (ML) applications, particularly in edge ML applications embedded in systems like robots, satellites, and unmanned vehicles. It examines the suitability of the IEEE Standard 1671 (IEEE Std 1671), known as the Automatic Test Markup Language (ATML), an XML-based standard originally developed for electronic systems, for ML application testing. The paper explores extending IEEE Std 1671 to encompass the unique challenges of ML applications, including the use of datasets and dependencies on software. Through modeling various tests such as adversarial robustness and drift detection, this paper offers a framework adaptable to specific applications, suggesting that minor modifications to ATML might suffice to address the novelties of ML. This paper differentiates ATML's focus on testing from other ML standards like Predictive Model Markup Language (PMML) or Open Neural Network Exchange (ONNX), which concentrate on ML model specification. We conclude that ATML is a promising tool for effective, near real-time operational T&E of ML applications, an essential aspect of AI lifecycle management, safety, and governance.