Responsibility Gap and Diffusion in Sequential Decision-Making Mechanisms
Junli Jiang, Pavel Naumov

TL;DR
This paper analyzes the computational complexity of responsibility diffusion and gaps in collective decision-making mechanisms, revealing their high complexity classes and intersections.
Contribution
It provides a formal complexity classification of responsibility diffusion and gap properties in decision mechanisms, a novel theoretical insight.
Findings
Diffusion-free mechanisms are $ ext{Pi}_2$-complete.
Gap-free mechanisms are $ ext{Pi}_3$-complete.
The intersection of diffusion-free and gap-free mechanisms is $ ext{Pi}_2$-complete.
Abstract
Responsibility has long been a subject of study in law and philosophy. More recently, it became a focus of AI literature. The article investigates the computational complexity of two important properties of responsibility in collective decision-making: diffusion and gap. It shows that the sets of diffusion-free and gap-free decision-making mechanisms are -complete and -complete, respectively. At the same time, the intersection of these classes is -complete.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
