Metraipolis › archive › dc_4264d4059ca6

Multimodal AI Detection for Math-Heavy Scientific Text — arXiv:2610.21062

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.21062
License (as archived)
CC0-1.0
Archived
2026-10-16T09:53:23.347Z
SHA-256 of the archived text
d46b4f3b5b75f6205dd66c18b058b764d63abfe89df0bb4ab9642756d9c9a94e
Stable URL of this page
https://metraipolis.com/documento/dc_4264d4059ca6

How to cite

Multimodal AI Detection for Math-Heavy Scientific Text — arXiv:2610.21062 — arXiv (en), https://arxiv.org/abs/2610.21062 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4264d4059ca6 (Metraipolis archive dc_4264d4059ca6, sha256 d46b4f3b5b75f6205dd66c18b058b764d63abfe89df0bb4ab9642756d9c9a94e)
BibTeX
@misc{dc4264d4059ca6,
  title = {Multimodal AI Detection for Math-Heavy Scientific Text — arXiv:2610.21062},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21062},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4264d4059ca6; sha256 d46b4f3b5b75f6205dd66c18b058b764d63abfe89df0bb4ab9642756d9c9a94e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21062. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As large language models become increasingly capable of generating, and assisting with, scientific writing, there is a need for greater transparency and disclosure around the use of AI in research. Consequently, a veritable subfield of research and a number of commercial services aim to flag AI-generated content automatically. However, existing detectors which rely only on text extracted from PDFs fail to benefit from the rich visual information contained in the formatting of math-heavy scientific content. To study this, we select human-written proof and prose passages from pre-2022 arXiv LaTeX sources and re-generate them using 15 modern LLMs within the context of the same paper. This leaves us with coupled human and AI outputs in three different representations: the LaTeX source, a rendered image of the PDF, and the text extracted from the PDF. We find that the accuracy of the state-of-the-art Pangram 4 drops significantly as the mathematical content in a passage increases, especially when evaluated on text as opposed to LaTeX. However, this is not an inherent limitation of detecting AI-generated math: finetuning Qwen-3.5-27B based detectors on this domain recovers the gap, with LaTeX inputs performing significantly better than text since they preserve more formatting information. Since LaTeX sources are rarely available in practice, we also train SnapJudge: an image-based detector operating on screenshots of both prose and proofs from papers. At 0.1% false positive rate, SnapJudge achieves a detection rate of 92% on proofs and 93% on prose generated by frontier models, substantially outperforming both Pangram 4 and our text-based detector. We release our data, models and code at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.21062 — 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 2026-10-16T08:44:47.620Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).