Published February 8, 2026
| Version v1
Publication
Open
Codex Benchmark: Governed Evolution vs Ungated Baselines
Authors/Creators
Description
This document specifies a minimal, reproducible benchmark that tests a single architectural claim:
Claim (empirical): For matched seeds, compute, and training schedule, an admissibility-
before-commit update rule reduces long-horizon drift and fabrication-like failure modes
compared to an ungated baseline, without collapsing task performance.
This benchmark is intentionally system-agnostic. It does not require disclosure of proprietary
invariants. It evaluates the observable consequence of governed updates: bounded behavior under
long-horizon stress.