# Monitoring AI systems: A Problem Analysis, Framework and Outlook

arXiv: https://arxiv.org/abs/2205.02562 · HTML: https://mlsanity.com/paper/2205.02562/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 18 references that are in the map.
- First posted on arXiv 5 May 2022.

## Builds on (most cited first, 2 of 2)

- [Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use cases](https://mlsanity.com/paper/2102.11965/) (2021)
- [Informative Features for Model Comparison](https://mlsanity.com/paper/1810.11630/) (2018)

## Abstract (arXiv)

Knowledge-based systems have been used to monitor machines and processes in the real world. In this paper we propose the use of knowledge-based systems to monitor other AI systems in operation. We motivate and provide a problem analysis of this novel setting and subsequently propose a framework that allows for structuring future research related to this setting. Several directions for further research are also discussed.