AI 中文总结
该研究围绕五个规范选择组织多种局部加法特征归因方法，通过公理矩阵比较，将常见失败模式与假设关联，为使用局部加法归因的研究提出十项报告清单，强调归因结果依数学假设而定且假设应报告
AI 中文摘要
特征归因方法是可解释人工智能的核心。其假设用多种数学语言表达，如合作博弈值、路径积分、梯度算子、扰动分布和反向传播规则。本综述为局部加法特征归因提出了一个通用框架。它围绕五个规范选择组织了Shapley、基于路径、梯度/反向传播、扰动和CAM风格的方法，然后通过逐个方法的公理矩阵比较这些方法，并将常见的失败模式与产生它们的假设联系起来。最后，本综述为使用局部加法归因的研究提出了一个十项报告清单。核心观点是归因结果仅相对于定义它们的数学假设才有意义，并且这些假设应该被报告。
英文摘要
Feature-attribution methods are central to explainable artificial intelligence. Their assumptions are expressed in several mathematical languages: cooperative-game values, path integrals, gradient operators, perturbation distributions, and backpropagation rules. This survey proposes a common framework for local additive feature attribution. It organizes Shapley, path-based, gradient/backpropagation, perturbation, and CAM-style methods around five specification choices: value function, reference, path, perturbation distribution, and conservation rule. It then compares these methods through an axiom-by-method matrix and links common failure modes, including baseline sensitivity, off-manifold perturbations, sanity-check failures, adversarial manipulation, and method disagreement, to the assumptions that produce them. Finally, the survey proposes a ten-item reporting checklist for studies that use local additive attributions. The central message is that attribution results are meaningful only relative to the mathematical assumptions under which they are defined, and that those assumptions should be reported.
Comments35 pages, 7 figures, and 19 tables. Ancillary files include the axiom matrix, reporting checklist, related-survey scoring, and review-corpus summary
