Preprint / scholarly article

Stop Recomputing for AI/LLMs: Proof-Carrying Skills for Compute-Saving Inference Reuse

K. Takahashi

Published
DOI
10.5281/zenodo.18490939

Full text PDF (Zenodo)

Abstract

The preprint introduces Proof-Carrying Skills, a no-meta framework that reuses verified skill executions to reduce repeated AI/LLM inference cost, using a deterministic bounded checker, observable anchors, gas-metered predicate evaluation, and replay-resistant receipts for fail-closed verification.

Keywords

  • proof-carrying skills
  • inference reuse
  • LLMs
  • compute saving
  • deterministic checker
  • no-meta boundary
  • observable anchors
  • bounded verification
  • receipts
  • replay resistance
  • OPVM

Identifiers and source records