Metraipolis › archive › dc_de6eb649bd9c
SimAuthor: Harnessing Foundation Models for Persistent Scientific Simulator Authoring — arXiv:2610.06257
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.06257
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:31:33.750Z
- SHA-256 of the archived text
3bde0cc582cbe04887596716b70556415ad5a05f8371fbd16159005e5724f6e1- Stable URL of this page
https://metraipolis.com/documento/dc_de6eb649bd9c
How to cite
SimAuthor: Harnessing Foundation Models for Persistent Scientific Simulator Authoring — arXiv:2610.06257 — arXiv, https://arxiv.org/abs/2610.06257 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_de6eb649bd9c (Metraipolis archive dc_de6eb649bd9c, sha256 3bde0cc582cbe04887596716b70556415ad5a05f8371fbd16159005e5724f6e1)
BibTeX
@misc{dcde6eb649bd9c,
title = {SimAuthor: Harnessing Foundation Models for Persistent Scientific Simulator Authoring — arXiv:2610.06257},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.06257},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_de6eb649bd9c; sha256 3bde0cc582cbe04887596716b70556415ad5a05f8371fbd16159005e5724f6e1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06257. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Foundation models can generate scientific code, but authoring a scientific simulator (an executable program encoding hypotheses about how mechanisms generate observable signals) requires iterative refinement. Scientific adequacy rarely admits a unique implementation or exact test, so simulators must instead be judged against limited real observations. We study this setting as scientific simulator authoring under weak empirical feedback, where distributional comparisons between simulated and real signals guide revision, and the target is the simulator itself rather than only its generated samples. We introduce SimAuthor, a persistent authoring harness that retains and revises executable simulators, separates scalar search scores from structured discrepancy feedback, and accumulates reusable implementation mechanisms. We evaluate SimAuthor on six biomedical tasks spanning cardiac and respiratory audio, photoplethysmography (PPG), and electrocardiography (ECG). Under a fixed 100-attempt budget, SimAuthor outperforms PUCT score search on all six tasks, generally outperforms textual-strategy optimization, and achieves the highest endpoint score on five of six. The authored simulators also improve on unseen recordings, transfer to independent pretrained representations, and yield substantial out-of-distribution gains in downstream ECG classification. Finally, 111 of 138 audited revisions alter program structure and account for 86.1% of the signed score improvement. These results suggest that persistent revision can progressively convert foundation-model knowledge into better executable scientific simulators from limited empirical evidence. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.06257 — 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 2026-10-06T05:27:05.873Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).