研究人员开发了 Shadow-Loom，一个开源框架，旨在从叙事中创建图形世界模型。该系统采用基于 Judea Pearl 工作的因果物理学和叙事物理引擎，通过悬念和惊悚等状态来分析读者参与度。虽然大型语言模型用于提取和审计等边界任务，但核心推理过程由在图上操作的类型化代码处理。 AI
影响 引入了一个新颖的叙事分析框架，将核心推理与 LLM 边界任务分开。
排序理由 该集群描述了一篇学术论文，其中详细介绍了用于叙事分析的实验性开源框架。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2605.02475v1 Announce Type: cross Abstract: Stories hold a reader's attention because they have causes, secrets, and consequences. Shadow-Loom is an experimental open-source framework that turns a narrative into a versioned graphical world model and lets two engines act on …
Stories hold a reader's attention because they have causes, secrets, and consequences. Shadow-Loom is an experimental open-source framework that turns a narrative into a versioned graphical world model and lets two engines act on it: a causal physics grounded in Pearl's ladder of…