Metraipolis › archive › dc_d41bed969803

Transformed in Translation: Two-Stage Structural Uncertainty in LLM-Based Scientific Autoformalization — arXiv:2609.14808

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.14808
License (as archived)
CC0-1.0
Archived
2026-10-16T00:31:06.682Z
SHA-256 of the archived text
35b1b44be956527c053bec71a5ad6e74587d6b5fd807106e31c924026ac8e222
Stable URL of this page
https://metraipolis.com/documento/dc_d41bed969803

How to cite

Transformed in Translation: Two-Stage Structural Uncertainty in LLM-Based Scientific Autoformalization — arXiv:2609.14808 — arXiv (en), https://arxiv.org/abs/2609.14808 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d41bed969803 (Metraipolis archive dc_d41bed969803, sha256 35b1b44be956527c053bec71a5ad6e74587d6b5fd807106e31c924026ac8e222)
BibTeX
@misc{dcd41bed969803,
  title = {Transformed in Translation: Two-Stage Structural Uncertainty in LLM-Based Scientific Autoformalization — arXiv:2609.14808},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.14808},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d41bed969803; sha256 35b1b44be956527c053bec71a5ad6e74587d6b5fd807106e31c924026ac8e222},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14808. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Scientific autoformalization turns verbal accounts into executable mathematics, but executable code does not settle which model has been constructed. We examine two sources of structural uncertainty: the formalizer that generates a response law, and the recurrence that turns that law into trajectories. In secondary analyses of an openly archived crossed experiment, we studied 320 response maps generated by two pinned language-model formalizers from five engineered cognitive accounts within one sparse quadratic grammar and 16 randomized blocks. With whole blocks held out, source-account identity was recovered at 78.8% accuracy (chance 20.0%) and formalizer identity at 96.3% (chance 50.0%; both p < 0.001). Program size was the stronger single feature family; a pre-specified exploratory comparison found no stable source-account predictive gain from local geometry beyond size. Holding every response map fixed, we then evaluated five recurrence families spanning 33 configurations and 1,013,760 finite-horizon trajectories. Added feedback, projection and leak produced sharply different outcome distributions. The consequential distinction was which comparisons survived: median cross-recurrence rank concordance was 0.73 for endpoint magnitude but 0.05 for settling, among the configuration pairs with defined rankings. Thus a common mathematical language did not erase translation provenance, and robust ordering under one observable did not transfer to another. Scientific autoformalization is usefully studied as model-space construction: the generated ensemble and its dynamical embedding are both part of the specification supporting a scientific claim.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-15 in cs.SE).
Categorie arXiv: Computational Physics (physics.comp-ph) ; Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2609.14808 — 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 2026-10-16T00:12:31.116Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).