LOAIMar 20

Capability Safety as Datalog: A Foundational Equivalence

arXiv:2603.2672528.81 citationsh-index: 7
Predicted impact top 22% in LO · last 90 daysOriginality Highly original
AI Analysis

This foundational equivalence enables the transfer of algorithmic results to capability safety, potentially impacting security and AI safety domains.

The paper proves that capability safety can be exactly represented as propositional Datalog evaluation, addressing limitations in the existing capability hypergraph framework such as lack of efficient incremental maintenance and decision procedures for audit surface containment.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes