Scratchy: Visual-Scratchpad Multimodal Reasoning for Cryptographic Proof Generation in EasyCrypt

Scratchy introduces a visual-scratchpad method for generating cryptographic proofs in EasyCrypt by converting natural-language security descriptions into a typed proof-relation graph and then into a visual proof state that guides multimodal language models. The approach exposes implicit proof-theoretic dependencies that LLMs struggle with, enabling clearer coordination of probability, adversarial games, invariants, assumptions, and bounds. Scratchy-eval, a 114-task dataset from official EasyCrypt files, demonstrates that classical LLMs achieve significant gains when using these structured visual proof states.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• multimodal
• safety