Work

PERTARO: Cache-Bounded Neuro-Symbolic Micro-Experts via Seed-Compressed Ternary Tries and Periodic Answer Set Regrounding

Year: 2026

Type: article

Abstract: Neuro-symbolic systems and sparse Mixture-of-Experts(MoE) architectures face competing structural pressures:Answer Set Programming (ASP) solvers suffer from combinatorial rule explosion when grounding deep sequentialhorizons, while micro-expert arrays require compact, deterministic representations for zero-heap embedded andbare-metal execution. We present PERTARO (PrunedExpert Regrounding Trie via Answer-set Reduct Optimization), a #![no_std], zero-dependency Rust primitive (released as pertaro v0.3.0) that unifies deterministic PRNG weight synthesis with bounded-horizon stablemodel semantics inside a sealed 256-byte word

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.23443780

Author: Sean Everett Morin

Language: English

Topic: Logic, Reasoning, and Knowledge

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W7222885247

FWCI:

Cites:

Cited by:

Related to: 10