Simplify evaluation instructions

README.md

@@ -30,7 +30,7 @@ python -m grounding_brep.serve \
   --checkpoint weights/brepground/model.safetensors
 ```
 
-The service uses decision threshold **0.925**. To evaluate the model, prepare the
+To evaluate the model, prepare the
 STEP dataset's graph cache and run `bash scripts/evaluate_grounding.sh`.
 See [dataset usage](https://github.com/JohanStackk/FutureCAD/blob/main/docs/dataset.md)
 for the label-reading convention and commands.