---
title: "Factuality"
description: "1 posts about Factuality, summarised, each linking to the original."
---

# Factuality
> 1 posts about Factuality, summarised, each linking to the original.

## Articles

### [Getting the Source Right, Not Just the Fact: Source-Aware Verification for MCP Agents](https://yomu.fyi/post/getting-the-source-right-not-just-the-fact-source-aware-verification-f.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Antonio Tiene, Ander Alvarez Sanz, Oliver Wirjadi
- Published: Sep 29, 2026
- Type: Problem & solution

MCP agents can produce claims that are factually true but attributed to the wrong source, a failure known as cross-source conflation that source-blind checkers miss. ProvenanceGuard preserves source identity by decomposing answers into claims, routing each to its relevant tool output, and checking support and attribution separately, using local models like MiniLM and DeBERTa. On medical agent traces with 281 interactions, it caught 138 of 139 claims experts flagged, scoring 0.802 F1 on blocking decisions and correct source 86% of the time. It flagged 67 supported claims for review under a cautious policy and added roughly half a second per answer in local tests. Blocked answers can be fixed through a repair loop for rewriting or fallback, avoiding unverifiable responses while keeping sensitive traces in a controlled environment.