# Hugging Face — Getting the Source Right, Not Just the Fact: Source-Aware Verification for MCP Agents

- Company: Hugging Face (huggingface.co)
- Announced: 2026-09-29T13:07:00+00:00
- Category: research-paper
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://huggingface.co/blog/MultiverseComputingCAI/getting-the-source-right-not-just-the-fact-source
- Record: https://forck.live/items/14976-getting-the-source-right-not-just-the-fact-source-aware-verification-for-mcp
- Subject: Platform

Hugging Face and Multiverse Computing released a paper introducing ProvenanceGuard, a post-generation verification layer for MCP-based LLM agents that checks whether each claim is supported by the specific source the answer attributes it to, rather than by any source in a pooled evidence set. In tests on 361 claims from a medical agent, it caught 138 of 139 claims that human experts said should not pass, while flagging 67 supported claims for review under a conservative setting.

## Evidence

Verbatim from https://huggingface.co/blog/MultiverseComputingCAI/getting-the-source-right-not-just-the-fact-source:

> The failure mode we care about is one we call cross-source conflation: a claim that is true somewhere in the evidence, but attributed to the wrong source. A source-blind verifier may pass it, because the fact does exist in the pool. A source-aware verifier should not.

---

Record: https://forck.live/items/14976-getting-the-source-right-not-just-the-fact-source-aware-verification-for-mcp
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md