Source credibility weighting and poisoned-page skepticism
Reference classes
OpenAI current estimate (inferred)
3/10 (0.50)
Anthropic current estimate (inferred)
4/10 (0.50)
Resolution
Source: OpenAI & Anthropic system cards, Preparedness / RSP updates, or independent audits
Includes: Public primary-source confirmation that Source credibility weighting and poisoned-page skepticism is operating across frontier deployments. Runtime/training safeguard on False information (robustness r = 58%).
Excludes: Aspirational roadmap commitments, offline toy-model pilots, or unverified third-party claims.