反事实图像审计的共同见证证书与精确特征边界
Common-Witness Certificates and Sharp Feature Bounds for Counterfactual Image Auditing
- Université du Québec à Trois-Rivières（魁北克三河大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究针对图像编辑器的局部到全局失效问题，提出共同见证框架分离审计与因果识别，通过 Helly 型论证等得到证书与边界，经多数据集实验验证方法有效性，用于审计声明特征关系而非像素级反事实。
AI中文摘要：
图像编辑器可能在没有单个潜在解释适配完整输出的情况下，分别满足每个区域的合理性约束。我们通过共同见证等级和见证神经来形式化这种从局部到全局的失效。该框架将审计与因果识别分离：仅共享外生性就允许每个 regime 边缘的耦合，而外部合理的见证关系为预定义图像特征提供精确的部分识别边界。Helly 型论证为准凸损失、异质作用层和有限见证图集提供了简短的不相容证书；阻断超图公式给出精确修复计数。regime 边缘的同时置信区间为完整识别区间提供有限样本外覆盖。受控 MNIST、Morpho-MNIST 和 smallNORB 研究证明了预测的局部-全局分离，而合成实验测试了精确边界、证书恢复和结构化计算。该方法审计声明的特征关系，不识别无限制的像素级反事实。
英文摘要：
An image editor may satisfy every regional plausibility constraint separately even when no single latent explanation fits the complete output. We formalize this local-to-global failure using a common witness grade and witness nerve. The framework separates auditing from causal identification: shared exogeneity alone allows every coupling of the regime marginals, whereas an externally justified witness relation yields sharp partial-identification bounds for prespecified image features. Helly-type arguments provide short incompatibility certificates for quasiconvex losses, heterogeneous action strata, and finite witness atlases; a blocker-hypergraph formula gives exact repair counts. Simultaneous confidence regions for the regime marginals give finite-sample outer coverage of the complete identified interval. Controlled MNIST, Morpho-MNIST, and smallNORB studies demonstrate the predicted local-global separation, while synthetic experiments test sharp bounds, certificate recovery, and structured computation. The method audits a declared feature relation and does not identify unrestricted pixel-level counterfactuals.
