Metraipolis › archive › dc_e178235feacb
NEMSim: Learning Control-Conditioned Multi-Event Physical Dynamics via Executable Event-Mechanism Priors — arXiv:2609.30718
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.30718
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T02:10:37.197Z
- SHA-256 of the archived text
58c76096dcce378e0b427a83a276896ab688119bb7fa0249094d4dcdaaef0d8e- Stable URL of this page
https://metraipolis.com/documento/dc_e178235feacb
How to cite
NEMSim: Learning Control-Conditioned Multi-Event Physical Dynamics via Executable Event-Mechanism Priors — arXiv:2609.30718 — arXiv (en), https://arxiv.org/abs/2609.30718 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e178235feacb (Metraipolis archive dc_e178235feacb, sha256 58c76096dcce378e0b427a83a276896ab688119bb7fa0249094d4dcdaaef0d8e)
BibTeX
@misc{dce178235feacb,
title = {NEMSim: Learning Control-Conditioned Multi-Event Physical Dynamics via Executable Event-Mechanism Priors — arXiv:2609.30718},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.30718},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e178235feacb; sha256 58c76096dcce378e0b427a83a276896ab688119bb7fa0249094d4dcdaaef0d8e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30718. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
High-fidelity simulation of control-conditioned multi-event physical systems is computationally expensive, especially across broad control spaces and long trajectories. In these systems, macroscopic evolution emerges from localized discrete events whose intensities and effects depend on process controls and evolving local states, while the available system knowledge is typically expressed as event-attribute descriptions. Purely data-driven surrogates must infer these event effects from limited trajectory coverage, which can hinder generalization to unseen control regimes. Physics-guided methods instead primarily build on equation-level constraints or differentiable solvers rather than discrete event-rule priors. We therefore propose NEMSim (Neural Event-Mechanism Simulator), which compiles predefined event-attribute descriptions into an executable transition structure linking control-dependent event intensities, prior-guided mechanism attribution, and state-dependent responses. To enable evaluation of control-conditioned multi-event dynamics with explicit system knowledge, we construct a 3D KMC-based benchmark pairing high-fidelity trajectories with explicit event rules, standardized splits, and evaluation protocols. Across three settings, NEMSim reduces Avg. RMSE by 58.9%-81.3% relative to the strongest baseline in each setting. It also remains best in the data-efficiency study with training-data fractions down to 10%. Mechanism analyses further show that these gains arise from executable rule integration rather than prior access or architecture alone. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.30718 — 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 2026-10-08T01:43:06.692Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).