将文献与数据整合为可导航的因果知识图谱，揭示局部证据间的矛盾与关联。
PROMETHEUS: Automating Deep Causal Research Integrating Text, Data and Models
- 构建局部因果模型的层叠结构，以显式覆盖研究领域并支持动态拼接
- 在三个案例中验证了对海洋温度、减重药物与红酒健康效应的深层因果分析
- 能基于原始数据与代码评估反事实假设，适合需要严谨因果推断的研究者
大语言模型可从文本中提取局部因果主张，但若将其组织为持久、可导航的世界模型，则更具价值。我们提出PROMETHEUS框架，将检索到的文献、报告、代理轨迹、源数据、代码、模拟结果和科学模型转化为因果图谱：基于显式研究底面覆盖的层叠式局部因果预测状态模型族。每个局部区域包含因果事件、结构化主张表、预测检验、支持统计与来源信息；限制映射用于比较重叠区域；粘合诊断揭示一致性、漂移、矛盾与信息不足。最终形成的拓扑世界模型并非单一全局图谱，而是一种研究工具，可引导用户定位文献中的观点、其位置、支持强度以及局部主张无法整合为统一全局视图之处。三个文献图谱案例——海洋温度对海洋种群的影响、GLP-1减重证据、白藜芦醇/红酒健康效益——展示了基于文本的深度因果研究，强调局部性、证据强度、持久状态与粘合张力。四个基于真实数据的反事实案例——《自然·气候变化》微塑料强迫研究、印度河谷水文研究（含VIC模型输出与代码）、经典萨克斯蛋白信号通路研究（单细胞扰动数据）及《自然》鸣叫鼠研究（MAPseq投影矩阵）——展示了更强模式：当论文发布源数据、模拟输出或代码时，PROMETHEUS可基于该科学底面评估反事实，并重建围绕它的层叠世界模型。
原文摘要 · Abstract (English)
Large language models can extract local causal claims from text, but those claims become more useful when organized as persistent, navigable world models rather than as flat summaries. We introduce PROMETHEUS, a framework that turns retrieved literature, filings, reviews, reports, agent traces, source data, code, simulations, and scientific models into causal atlases: sheaf-like families of local causal predictive-state models over an explicit cover of a research substrate. Each local region contains causal episodes, structured claim tables, predictive tests, support statistics, and provenance; restriction maps compare overlapping regions; gluing diagnostics expose agreement, drift, contradiction, and underdetermination. The resulting Topos World Model is not a single universal graph. It is a research instrument for navigating what a corpus says, where it says it, how strongly it is supported, and where local claims fail to assemble into a coherent global view. Three literature-atlas case studies -- ocean-temperature impacts on marine populations, GLP-1 weight-loss evidence, and resveratrol/red-wine health-benefit claims -- illustrate deep causal research from text with explicit locality, evidence, persistent state, and gluing tension. Four grounded-counterfactual case studies -- a Nature Climate Change microplastics forcing paper, an Indus Valley hydrology paper with VIC-derived figure data and model code, the canonical Sachs protein-signaling study with single-cell perturbation data, and a Nature singing-mouse study with MAPseq projection matrices -- show a stronger mode: when a paper ships source data, simulation outputs, or code, PROMETHEUS can evaluate a counterfactual against that scientific substrate and then rebuild the sheaf world model around the
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。