Common-Witness Certificates and Sharp Feature Bounds for Counterfactual Image Auditing

2026-09-03

AI Summary

该研究通过共同见证等级和见证神经，解决图像编辑中局部合理性与全局解释不一致的问题，并提出了一种新的审计框架来评估特定图像特征。

Abstract

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.

Problem

• common witness
• feature bounds
• counterfactual image auditing

Innovation

• common witness grade
• witness nerve
• sharp partial-identification bounds
• Helly-type arguments
• blocker-hypergraph formula