Metraipolis › archive › dc_dd93f6bf065e

ForTress: Bringing Assurance and Determinism for LLM-Driven Fortran-to-Python Translation — arXiv:2610.22528

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.22528
License (as archived)
CC0-1.0
Archived
2026-10-19T09:37:10.452Z
SHA-256 of the archived text
54196feaef8a5c2f81d5830ee4186528e094dd845c22c8db9be50be5c3e63ce2
Stable URL of this page
https://metraipolis.com/documento/dc_dd93f6bf065e

How to cite

ForTress: Bringing Assurance and Determinism for LLM-Driven Fortran-to-Python Translation — arXiv:2610.22528 — arXiv (en), https://arxiv.org/abs/2610.22528 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dd93f6bf065e (Metraipolis archive dc_dd93f6bf065e, sha256 54196feaef8a5c2f81d5830ee4186528e094dd845c22c8db9be50be5c3e63ce2)
BibTeX
@misc{dcdd93f6bf065e,
  title = {ForTress: Bringing Assurance and Determinism for LLM-Driven Fortran-to-Python Translation — arXiv:2610.22528},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.22528},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dd93f6bf065e; sha256 54196feaef8a5c2f81d5830ee4186528e094dd845c22c8db9be50be5c3e63ce2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22528. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Modernizing mature scientific software from Fortran to Python can improve accessibility and integration with modern computing tools, but manual rewriting is expensive. Large language models (LLMs) make translation more practical, yet generated code can pass regression tests while violating source-language semantics, and contextual corrections may not persist across subsequent translations. We present ForTress, which solidifies recurring LLM translation decisions into guarded executable rules for deterministic reuse and provides semantic assurance for a non-trivial subset of these rules. Its LLM-assisted auditing process expresses universally quantified preservation obligations over mechanized Fortran and Python semantics in Lean. Human experts review semantic fidelity and correspondence with production rules, and Lean's kernel checks proofs and refutations under explicit assumptions. These audit records expose the conditions either supporting correctness or identifying failure cases. We evaluate ForTress on 17 benchmarks from 15 scientific software spanning diverse domains. The translated programs achieve bitwise-identical with native Fortran on all evaluated tests under the recorded execution and initialization configurations. Against these software, ForTress accumulates 193 executable rules and 188 audit records, of which 121 have checked soundness proofs, including 31 established after counterexample-guided refinement. Cross-software reuse exceeds 90% for 14 of the 15 software. Even with additional assurance and determinism, the LLM usage cost is 44.2% lower than direct LLM translation.

Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.SE, nuovi lavori del giorno).
Categorie arXiv: Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2610.22528 — 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 2026-10-19T09:31:59.695Z dalla pagina https://arxiv.org/list/cs.SE/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).