Metraipolis › archive › dc_d50e649fbeed

Scratchy: Visual-Scratchpad Multimodal Reasoning for Cryptographic Proof Generation in EasyCrypt — arXiv:2609.06226

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.06226
License (as archived)
CC0-1.0
Archived
2026-10-16T13:40:07.258Z
SHA-256 of the archived text
6cc3853aed60d63685e5efcd8182f0c01c27f48daf9d54e9411f2f596f667c8b
Stable URL of this page
https://metraipolis.com/documento/dc_d50e649fbeed

How to cite

Scratchy: Visual-Scratchpad Multimodal Reasoning for Cryptographic Proof Generation in EasyCrypt — arXiv:2609.06226 — arXiv (en), https://arxiv.org/abs/2609.06226 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d50e649fbeed (Metraipolis archive dc_d50e649fbeed, sha256 6cc3853aed60d63685e5efcd8182f0c01c27f48daf9d54e9411f2f596f667c8b)
BibTeX
@misc{dcd50e649fbeed,
  title = {Scratchy: Visual-Scratchpad Multimodal Reasoning for Cryptographic Proof Generation in EasyCrypt — arXiv:2609.06226},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.06226},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d50e649fbeed; sha256 6cc3853aed60d63685e5efcd8182f0c01c27f48daf9d54e9411f2f596f667c8b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06226. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) have recently made substantial progress in formal proof generation, yet presenting distinctive challenges in cryptographic area. Computational security arguments posit that a valid proof must coordinate probability, adversarial games, invariants, assumptions and bounds, which can be provided by a machine-checked framework named EasyCrypt. Although all objects may appear in available context, LLMs still struggle because proof-theoretic dependencies are typically implicit in a linear representation and distributed across multiple programs. So, this paper presents Scratchy, a visual-scratchpad approach that exposes these dependencies for multimodal generation. Given the natural-language security description, with formal context and target propositions, the proof objects can be normalized into a typed proof-relation graph. Then a structure-preserving visual compiler transforms the graph into the formula-rich visual proof state that guides a multimodal model in generating the EasyCrypt proof. Also, the Scratchy-eval, a 114-task dataset derived from reliable official EasyCrypt files, has been introduced. It contains 64 security-form proof generations and 50 multiple-choice knowledge tests. After a series of evaluations, covering semantic grounding, relational invariants, and game reductions, classical LLMs like GPT-5.6-Sol and Claude-Opus-5 have gained a clear advantage from Scratchy's structured visual proof states. This contrast suggests that explicit proof structure can make the improvement and multimodal proof-state representation as a promising direction for computer-aided cryptography.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.06226 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T13:09:48.409Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).