Clarify DungeonEscape checkpoint is provisional

README.md

@@ -132,12 +132,13 @@ Gymnasium / MuJoCo scores.
 |---|---:|---:|---:|---|---:|---:|
 | `dungeon-escape/dungeonescape-b36.onnx` | 32 | 36 | 371 | `Discrete(7)` logits | 0.2222 | 41.67% |
 
-This is an initial checkpoint published so the end-to-end workflow can be tested;
-the model and metrics may be replaced by a stronger checkpoint later. The
-measurement above is one deterministic first-episode pass over the 36-agent
-scene (12 independent arenas × three cooperative agents), using a compatible
-local release-23 build. The matching model-removed build is published separately
-in the environment repo.
+This is an **intermediate training checkpoint** published to validate the
+end-to-end download and evaluation workflow. Its reported performance is
+provisional and does not represent the final trained policy. The artifact and
+metrics will be updated after training completes. The measurement above is one
+deterministic first-episode pass over the 36-agent scene (12 independent arenas
+× three cooperative agents), using a compatible local release-23 build. The
+matching model-removed build is published separately in the environment repo.
 
 DungeonEscape is decentralized cooperative control. Each three-agent match is
 stored as three linked ego-agent trajectories, and the same shared policy is