urlhealth

Open-source URL liveness/hallucination classifier released by Rao, Wong & Callison-Burch alongside their citation-reliability study (arXiv:2604.03173, 2026, "Detecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research Agents") — a concrete mitigation tool for the URL- hallucination problem their paper measures across ten commercial LLMs and deep research agents.

First encountered 2026-10-21, mentioned in passing in the same capture that surfaced the paper's "fabricated snippets" terminology; not yet independently tested or described elsewhere in this vault. Watching for recurrence.

References

• claim-rao-wong-callison-burch-2026-fabricated-snippets-named-not-yet-systematically-studied
• Capture: 10-inbox/raw/2026-10-21-has-ai-safety-or-nlp-evaluation-literature-named.md