# humancompatible.interconnect: Testing Properties of Repeated Uses of Interconnections of AI Systems

arXiv: https://arxiv.org/abs/2507.09626 · HTML: https://mlsanity.com/paper/2507.09626/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 35 references that are in the map.
- First posted on arXiv 13 Jul 2025.

## Builds on (most cited first, 13 of 13)

- [Automated Design of Agentic Systems](https://mlsanity.com/paper/2408.08435/) (2024)
- [Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach](https://mlsanity.com/paper/1801.10578/) (2018)
- [Gradient Masking Causes CLEVER to Overestimate Adversarial Perturbation Size](https://mlsanity.com/paper/1804.07870/) (2018)
- [On the Ergodic Control of Ensembles](https://mlsanity.com/paper/1807.03256/) (2018)
- [On Extensions of CLEVER: A Neural Network Robustness Evaluation Algorithm](https://mlsanity.com/paper/1810.08640/) (2018)
- [Predictability and Fairness in Load Aggregation and Operations of Virtual Power Plants](https://mlsanity.com/paper/2110.03001/) (2021)
- [Bayesian calibration of differentiable agent-based models](https://mlsanity.com/paper/2305.15340/) (2023)
- [Closed-Loop View of the Regulation of AI: Equal Impact across Repeated Interactions](https://mlsanity.com/paper/2209.01410/) (2022)
- [Iterated Function Systems: A Comprehensive Survey](https://mlsanity.com/paper/2211.14661/) (2022)
- [Optimal Transport for Fairness: Archival Data Repair using Small Research Data Sets](https://mlsanity.com/paper/2403.13864/) (2024)
- [Predictability and Fairness in Social Sensing](https://mlsanity.com/paper/2007.16117/) (2020)
- [On the Ergodic Control of Ensembles in the Presence of Non-linear Filters](https://mlsanity.com/paper/2112.06767/) (2021)
- [Iterated Piecewise-Stationary Random Functions](https://mlsanity.com/paper/1909.10093/) (2019)

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

- [Stochastic Sample Approximations of (Local) Moduli of Continuity](https://mlsanity.com/paper/2509.15368/) (2025)

## Abstract (arXiv)

Artificial intelligence (AI) systems often interact with multiple agents. The regulation of such AI systems often requires that em a priori/ guarantees of fairness and robustness be satisfied. With stochastic models of agents' responses to the outputs of AI systems, such em a priori/ guarantees require non-trivial reasoning about the corresponding stochastic systems. Here, we present an open-source PyTorch-based toolkit for the use of stochastic control techniques in modelling interconnections of AI systems and properties of their repeated uses. It models robustness and fairness desiderata in a closed-loop fashion, and provides em a priori/ guarantees for these interconnections. The PyTorch-based toolkit removes much of the complexity associated with the provision of fairness guarantees for closed-loop models of multi-agent systems.