Claude 85e62e6600 feat(benchmarks): add RVF intelligence benchmark (baseline vs learning) ... Adds head-to-head cognitive benchmark comparing stateless baseline against full RVF-learning pipeline (witness chains, coherence monitoring, authority guards, budget tracking, ReasoningBank). Measures accuracy, learning curves, reasoning efficiency, and meta-cognitive quality across configurable episodes. Results: RVF-learning shows +1.1 IQ delta with higher reasoning coherence (0.98 vs 0.95) and efficiency (0.91 vs 0.83) at difficulty 1-10. https://claude.ai/code/session_01RnwD4x5cbpB7FPvoyYQz8G		2026-02-15 19:59:29 +00:00
..
src	feat(benchmarks): add RVF intelligence benchmark (baseline vs learning)	2026-02-15 19:59:29 +00:00
tests	style: apply rustfmt across entire codebase	2026-01-28 17:00:26 +00:00
Cargo.toml	feat(benchmarks): add RVF intelligence benchmark (baseline vs learning)	2026-02-15 19:59:29 +00:00