Metraipolis › archive › dc_463e97082292
Beyond Correctness: Attribution of Natural-Language Documentation for Formal Libraries — arXiv:2610.33094
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.33094
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T07:59:35.903Z
- SHA-256 of the archived text
402768b102c947f0f32d849690d764e0c6b6b9218964408fc6b106d4b7ca8dd2- Stable URL of this page
https://metraipolis.com/documento/dc_463e97082292
How to cite
Beyond Correctness: Attribution of Natural-Language Documentation for Formal Libraries — arXiv:2610.33094 — arXiv (en), https://arxiv.org/abs/2610.33094 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_463e97082292 (Metraipolis archive dc_463e97082292, sha256 402768b102c947f0f32d849690d764e0c6b6b9218964408fc6b106d4b7ca8dd2)
BibTeX
@misc{dc463e97082292,
title = {Beyond Correctness: Attribution of Natural-Language Documentation for Formal Libraries — arXiv:2610.33094},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.33094},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_463e97082292; sha256 402768b102c947f0f32d849690d764e0c6b6b9218964408fc6b106d4b7ca8dd2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.33094. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Formal languages are widely used in software engineering to specify and verify program properties. Because their mathematical notation and logic are hard to read, developers often rely on natural-language documentation to understand the functions in formal libraries. Yet a documentation statement can be provably true and still hold after the function's behavior changes. We call a statement's dependence on the function's specific behavior attribution, and we give a method to check it. We design and implement DocAuth, a documentation-generation method that uses attribution to decide what to publish and attaches to each published sentence the formal property recovered from it, together with checkable evidence. On 150 functions from the Community Books library of the ACL2 theorem prover, three large language models produce proved but non-attributable properties for about a third of the functions. DocAuth matches or exceeds the attribution rate of a mutation-based filter while delivering 37% more attributable sentences. Compared with a pipeline that checks truth alone, it raises the share of published sentences that a second model confirms as attributable from 82.9% to 94.7%. These results show that provable truth does not guarantee that documentation reflects what a function actually does. Attribution complements truth as a criterion for generating and evaluating documentation for formal libraries. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.33094 — 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 2026-10-27T07:55:30.809Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).