Capability Safety as Datalog: A Foundational Equivalence
Not on the map. Why?
Abstract (arXiv)
We prove that capability safety admits an exact representation as propositional Datalog evaluation (Datalogprop: the monadic, ground, function-free fragment of first-order logic), enabling the transfer of algorithmic and structural results unavailable in the native formulation. This addresses two structural limitations of the capability hypergraph framework of Spera [2026]: the absence of efficient incremental maintenance, and the absence of a decision procedure for audit surface containment. The equivalence is tight: capability hypergraphs correspond to exactly this fragment, no more.
Key facts. Cited by 2 papers in the map (data through 13 Oct 2026). Builds on 4 of its 25 references that are in the map. First posted on arXiv 20 Mar 2026.
Builds on
4 of 25 references.
References · 4
- 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,904
- 2023TaskBench: Benchmarking Large Language Models for Task Automationcited by 141
- 2017AI Safety Gridworldscited by 108
- 2026Safety is Non-Compositional: A Formal Framework for Capability-Based AI Systemscited by 4
Built on by
Citing papers per year: 2026: 2.
2 papers.