arXiv：cs.LG· Yiwei Liu, Luwei Yang, Shunbo Lei·· 3 小时前
未实现影响的因果命运动力学
Causal-fate dynamics of unrealized influence
AI 导读
研究者提出“因果命运动力学”框架，将系统生成的影响划分为已实现、保持潜隐或被后续动力学转化三种命运，并在映射明确时给出精确的有限传输表示。该框架以线虫连接组模型、互联网路由观测和一种显式传输并选择性实现潜隐上下文影响的 Transformer 架构三项研究加以验证。论文共 39 页，含 6 幅图和 14 张补充表。
正文
Abstract:Many dynamical systems generate influences whose consequences are not fully exhausted in the realized trajectory at the moment they arise. Such consequences are often treated as absent, delayed or statically stored, leaving unclear how unrealized influence retains future relevance as the system evolves. Here we formulate causal-fate dynamics, in which generated influence may be realized, remain latent, or be transformed by subsequent dynamics, and give an exact finite-transport representation when the relevant maps are specified. A connectome-constrained Caenorhabditis elegans model first motivates the biological hypothesis that unresolved inter-neuronal influence may persist and contribute to later propagation; it does not establish such a mechanism in living animals. We next examine operational Internet routing, where a dynamically updated cross-observer history retains predictive information beyond the current local route state. We then use the representation to construct a Transformer architecture that explicitly transports and selectively realizes latent contextual influence while retaining language-modeling function. The three studies distinguish a model-motivated scientific hypothesis, an observational phenomenon compatible with future-relevant history and an executable construction for carrying unrealized influence through subsequent computation.
| Comments: | 39 pages (20-page main text and 19-page Supplementary Information), 6 figures, 14 supplementary tables. Code: this https URL |
| Subjects: | Systems and Control (eess.SY); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.11422 [eess.SY] |
| (or arXiv:2610.11422v1 [eess.SY] for this version) | |
| https://doi.org/10.48550/arXiv.2610.11422 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yiwei Liu [view email]
[v1]
Thu, 8 Oct 2026 07:48:53 UTC (395 KB)
来源：arXiv：cs.LG · arxiv.org