本文介绍了一个新颖的范畴框架，用于在Frobenius Markov范畴内理解无穷小因果关系。文章详细阐述了干预如何被视为现有复制/丢弃结构的切线变形，并与代数和几何Frobenius性质相互作用。该研究将这些概念与结构因果模型和Pearl的do-演算联系起来，为干预身份和信息流提供了新的视角。 AI
影响 引入了一个新的理论框架来理解AI系统中的因果关系。
排序理由 该集群包含一篇关于AI和数学理论主题的新学术论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2606.24621v1 Announce Type: cross Abstract: This paper introduces a categorical account of infinitesimal causality in Frobenius Markov categories equipped with tangent-bundle semantics. IDC captures the infinitesimal layer in which interventions act as tangent deformations …
This paper introduces a categorical account of infinitesimal causality in Frobenius Markov categories equipped with tangent-bundle semantics. IDC captures the infinitesimal layer in which interventions act as tangent deformations of copy/discard structure. Two distinct Frobenius …
This paper introduces a categorical account of infinitesimal causality in Frobenius Markov categories equipped with tangent-bundle semantics. IDC captures the infinitesimal layer in which interventions act as tangent deformations of copy/discard structure. Two distinct Frobenius …