Metraipolis › archive › dc_590db2e836b4
MOSAIC-SR: Transformer-Guided Symbolic Regression for Scientific Equation Recovery — arXiv:2609.20997
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.20997
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T01:44:33.522Z
- SHA-256 of the archived text
c14935002901c77ba2d23885751493c97079de0350dab2e2766276784eb5503e- Stable URL of this page
https://metraipolis.com/documento/dc_590db2e836b4
How to cite
MOSAIC-SR: Transformer-Guided Symbolic Regression for Scientific Equation Recovery — arXiv:2609.20997 — arXiv (en), https://arxiv.org/abs/2609.20997 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_590db2e836b4 (Metraipolis archive dc_590db2e836b4, sha256 c14935002901c77ba2d23885751493c97079de0350dab2e2766276784eb5503e)
BibTeX
@misc{dc590db2e836b4,
title = {MOSAIC-SR: Transformer-Guided Symbolic Regression for Scientific Equation Recovery — arXiv:2609.20997},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.20997},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_590db2e836b4; sha256 c14935002901c77ba2d23885751493c97079de0350dab2e2766276784eb5503e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20997. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Symbolic regression aims to recover closed-form equations from observations, providing interpretable models for scientific discovery. Existing approaches struggle to combine flexible structural search with efficient inference. Search-based methods can refine expression structure but often rely on costly combinatorial optimization with random initialization. Pretrained neural models generate formulas almost instantly, but their predictions often contain symbolic errors. We introduce MOSAIC-SR, which uses a pretrained Transformer to propose multiple initial sketches. These sketches initialize searches in several promising regions, avoiding random starts in the vast expression space. Each search jointly recovers structure and constants through scale-aware constant optimization and local symbolic repair. We evaluate MOSAIC-SR on the SRSD-Feynman dataset with and without dummy variables and on six additional benchmarks. MOSAIC-SR obtains the highest symbolic solution rate on every dataset while ranking among the top two methods in predictive accuracy. This advantage persists in the presence of irrelevant dummy inputs. The results show that learned priors can focus search on promising equation structures, and that numerical optimization and symbolic repair are important for recovery. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-21 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.20997 — 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 2026-10-10T01:14:16.601Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).