Same data, different verdicts: canonicalization and receipt lessons from IETF 127
At the IETF 127 Hackathon (San Francisco, 14–15 November 2026), several projects working on verifiable evidence of AI agent actions asked other people to write verifiers from their documents alone. Each implementation passed its own tests. The failures appeared between implementations. This post collects the concrete ones, checked against the slides and drafts, and notes what they mean for VAP,…
At the IETF 127 Hackathon in San Francisco on November 14-15, 2026, several AI verification projects sought to have others create verifiers using their documentation alone. The results showed discrepancies between implementations. This report details the specific issues, their implications for the VAP framework, and the lessons learned.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.