智能AI None 多重中介的诅咒：激活补丁中隐藏的交互效应 27510v1 Announce Type: new Abstract: Activation patching is the primary tool in mechanistic interpretability。 the and causal 2026-06-29 Sankaran Vaidyanathan, David Arbour, Aaron Mueller, Scott Niekum, David Jensen
开源推荐 None GitHub 热门项目：基于 LLM 的因果发现 项目 LLM-based-causal-discovery 是近期热门的开源项目。仓库地址：https://github。com/WXY604/LLM-based-causal-discovery Stars：837 作者：WXY604 项 项目 LLM based 2026-06-28 GitHub Trending
智能AI None 超越 Shapley：非对称 Shapley 值的高效计算 25103v1 Announce Type: new Abstract: We address the problem of explainability in machine learning models through feature the causal ASV 2026-06-25 Ezequiel Companeetz, Santiago Cifuentes, Sergio Abriola
智能AI None 联合因果发现和推理的调查 23741v1 Announce Type: new Abstract: Causal reasoning, which encompasses the discovery of causal structures and the infe and the data 2026-06-24 Xianjie Guo, Yuwei Wang, Guodu Xiang, Xiaoli Tang, Kui Yu, Han Yu, Qiang Yang
智能AI None CIExplainer++：为图神经网络生成因果和可解释的解释 arXiv:2606.20747v1 Announce Type: new Abstract: Explainable Artificial Intelligence aims to make black-box models more t the and causal 2026-06-23 Francisco Caldas, Sahil Satish Kumar, Ruben Belo, Cl\'audia Soares
智能AI None 模型选择在因果推理中的关键作用：药物警戒 InferBERT 框架内分类模型的比较分析 17113v1 Announce Type: new Abstract: Distinguishing causal adverse drug events (ADEs) from spurious correlations remains and the causal 2026-06-17 Csaba Kiss, Roland Molontay, Gabriele Pergola
智能AI None 关系结构因果模型 arXiv:2606.14892v1 Announce Type: new Abstract: An artificial intelligence must have a model of its environment that is causal and relational 2026-06-16 Adiba Ejaz, Elias Bareinboim
智能AI None TTCD：Transformer 从非平稳时间序列数据中集成时间因果发现 arXiv:2605.08111v1 Announce Type: new Abstract: The widespread availability of complex time series data in various domai and causal the 2026-05-12 Omar Faruque, Sahara Ali, Xue Zheng, Jianwu Wang