Update v2 release assets

README.md

@@ -16,16 +16,16 @@ models:
 
 # Representation over Routing Demo
 
-Interactive demo for the preprint **"Representation over Routing: Overcoming Surrogate Hacking in Multi-Timescale PPO"**.
+Interactive demo for the preprint **"Representation over Routing: Diagnosing Temporal Routing Pathologies in Multi-Timescale PPO"**.
 
-This Space visualizes the four pretrained ablation-stage agents from the associated model repository. The default selection shows **Stage 4: Target Decoupling**, the proposed method, performing a LunarLander rollout with a fixed deterministic demo seed.
+This Space visualizes four pretrained diagnostic-stage agents from the associated model repository. The default selection shows **Stage 4: Target Decoupling**, a structural separation variant, performing a LunarLander rollout with a fixed deterministic demo seed.
 
 ## Links
 
 * **Paper:** https://arxiv.org/abs/2604.13517
 * **Model Weights:** https://huggingface.co/ben-dlwlrma/Representation-Over-Routing
-* **GitHub Repository:** https://github.com/ben-dlwlrma/Representation-Over-Routing
+* **GitHub Code Repository:** https://github.com/ben-dlwlrma/Representation-Over-Routing
 
 ## Notes
 
-The paper experiments were conducted on `LunarLander-v2`. This hosted demo uses `LunarLander-v3` for compatibility with current Gymnasium releases, while keeping the same actor architecture and pretrained weights.
+The paper experiments were conducted on `LunarLander-v2`. This hosted demo uses `LunarLander-v3` for compatibility with current Gymnasium releases, while keeping the same actor architecture and pretrained weight format. The Space is a qualitative visualization, not an additional benchmark result.