发表机构
Integreat: Norwegian Centre for Knowledge-driven Machine Learning, University of Oslo; University of Oslo; Norwegian Computing Center（奥斯陆大学 Integreat：知识驱动机器学习挪威中心; 奥斯陆大学; 挪威计算中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出受限范围回溯反事实，允许建模者指定可变化的外生坐标，通过跨世界核控制替代值合理性，并给出推断、边界及策略表示条件，在示例和基准上验证了其解释能力。
AI 中文摘要
干预性反事实通过保持单元的外生背景固定，同时替换变量$A$的赋值，来评估诸如“如果$A$为$a$”这样的陈述。回溯反事实则反转了这一逻辑：它们保留结构赋值，而允许背景条件在不同世界之间变化。这种语义对于诊断性解释是自然的，但完全回溯可能过于宽松，因为每个外生坐标都可以变化。我们引入了受限范围回溯反事实，其中建模者指定哪些坐标可以变化，而其余坐标在不同世界之间共享。该范围决定了对比的可接受载体，而跨世界核则控制其替代值的合理性。我们提出了针对一般受限范围回溯反事实的基于模型的推断方法，为指定的解释性查询推导出尖锐的边际界限，并建立了该解释性查询允许修正值策略表示的前沿和兼容性条件。一个线性-高斯示例区分了局部噪声、祖先、无关噪声和不可行解释在不同范围内的表现，而对UCI成人基准的应用则说明了核的设定、敏感性以及解释中有多少是由跨世界耦合本身承载的。
英文摘要
Interventional counterfactuals evaluate statements such as "had $A$ been $a$" by replacing the assignment for $A$ while keeping the unit's exogenous background fixed. Backtracking counterfactuals reverse this logic: they preserve the structural assignments and instead vary background conditions across worlds. This semantics is natural for diagnostic explanation, but full backtracking may be too permissive because every exogenous coordinate can vary. We introduce scope-restricted backtracking counterfactuals, in which the modeler specifies which coordinates may vary while the remainder are shared across worlds. The scope determines the admissible carriers of the contrast, while a cross-world kernel governs the plausibility of their alternative values. We present model-based inference for general scope-restricted backtracking counterfactuals, derive sharp marginal bounds for a specified explanatory query, and establish frontier and compatibility conditions under which this explanatory query admits a modified-value policy representation. A linear-Gaussian example distinguishes local-noise, ancestor, irrelevant-noise, and infeasible explanations across scopes, while an application to the UCI Adult benchmark illustrates kernel specification, sensitivity, and how much of the explanation is carried by the cross-world coupling itself.
