Update README.md

README.md

@@ -24,9 +24,3 @@ Standard generative reward models (GRMs) couple principle generation with respon
 - **Stage 2** `P(J, r | Q, P, R)` — judge the response under pre-defined principles
 
 This ensures conditional independence `I(P; R | Q) = 0`, and enables **Principle Cache** — generating principles once per prompt and reusing them across all sampled responses in a GRPO group.
-
-## Results
-
-- **WritingBench 87.6** / **CW-v3 77.8** with Qwen3-8B + IP-GRM (competitive with GPT-5.2 and Claude-Sonnet-4)
-- **23.66% faster** reward computation than baseline GRM via Principle Cache
-