SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

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 s

Read original source ↗ Open in workspace

recordType

paper

region

Global