Tag
This paper presents a design-science audit protocol for detecting supervision drift in proxy-labeled credit-risk prediction models, with multi-signal diagnostics tested on LendingClub data.
This paper introduces a methodological framework for auditing the robustness and fidelity of post-hoc explainable AI tools like SHAP and LIME, combining these metrics into a Trust Score. It applies the framework to a food security dataset in Madagascar, highlighting the necessity of auditing XAI outputs for trustworthy decision-making in sensitive domains.
Stage–Audit introduces a governance protocol for Seed2Frontier discovery of cross-wiki tables, using disjoint curator-auditor write rights and a 12-check audit taxonomy to improve source-frontier precision by 42% relative over vanilla LLM curators.