Metraipolis › archive › dc_cb7b3a87f004

CAPRI: Contract-Aware Proof Repair for Isabelle — arXiv:2608.13459

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.13459
License (as archived): CC0-1.0
Archived: 2026-10-19T04:18:34.062Z
SHA-256 of the archived text: 274cb8fa04aff74bfdbd2a74ac8b48cc67fc6cda99f20f62965cdb040514830e
Stable URL of this page: https://metraipolis.com/documento/dc_cb7b3a87f004

How to cite

CAPRI: Contract-Aware Proof Repair for Isabelle — arXiv:2608.13459 — arXiv (en), https://arxiv.org/abs/2608.13459 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cb7b3a87f004 (Metraipolis archive dc_cb7b3a87f004, sha256 274cb8fa04aff74bfdbd2a74ac8b48cc67fc6cda99f20f62965cdb040514830e)

BibTeX

@misc{dccb7b3a87f004,
  title = {CAPRI: Contract-Aware Proof Repair for Isabelle — arXiv:2608.13459},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.13459},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cb7b3a87f004; sha256 274cb8fa04aff74bfdbd2a74ac8b48cc67fc6cda99f20f62965cdb040514830e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13459. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We address the use of large language models (LLMs) to help discover Isabelle proofs. An Isabelle build establishes that the submitted theory is accepted, but not that an LLM changed only what the developer authorised. We present CAPRI, a contract-aware repair workflow in which Isabelle checks the proof and an independent checker enforces a machine-readable edit contract. Prompts, proposals, candidate repositories, diagnostics, verdicts, and hashes are retained for audit. We evaluate five workflows on twelve failed proofs from four developments, with three replicates per task and condition, giving 180 runs and 138 valid repairs. Of 144 terminal candidates accepted by Isabelle, six had modified protected text; all arose in iterative workflows that could edit a complete theory. A proof-body-only interface produced 29/36 valid repairs and no contract violations, compared with 31/36 for the corresponding full-theory workflow. One-shot repair produced 22/36, while a later prospectively frozen iterative workflow produced 32/36; these figures compare complete workflows rather than individual mechanisms. A separate post hoc OpenRouter campaign found no improvement in the designated Luna comparisons. A Sol configuration with matched demonstrations produced 33/36 repairs, compared with 29/36 in the frozen OpenAI Responses condition, but the difference was not statistically significant in a one-sided exact McNemar test ($p=0.0625$).

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.AI).
Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI); Logic in Computer Science (cs.LO).
Pagina del lavoro: https://arxiv.org/abs/2608.13459 — 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 2026-10-19T04:13:06.773Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).