Tighten the model card wording

README.md

@@ -44,16 +44,16 @@ Same simulator, same episode seeds (`--seed=1000`), 200 episodes, 95% Wilson int
 | Policy | Training steps | Success | 95% CI |
 |---|---|---|---|
 | official [`lerobot/act_aloha_sim_transfer_cube_human`](https://huggingface.co/lerobot/act_aloha_sim_transfer_cube_human) | 80k | 81.0% (162/200) | 75.0-85.8 |
-| **this model** (seed 1000) | 80k | **75.5%** (151/200) | 69.1-80.9 |
+| this model (seed 1000) | 80k | 75.5% (151/200) | 69.1-80.9 |
 | same run at 50k steps | 50k | 64.0% (128/200) | 57.1-70.3 |
 | second seed (1001) at 50k steps | 50k | 62.0% (124/200) | 55.1-68.4 |
 
 The intervals of this model and the official checkpoint overlap; the two are statistically
 indistinguishable at this sample size. The 50k checkpoints are clearly below the baseline.
 
-Two things the per-checkpoint evaluations showed (details in the GitHub README):
-the training loss is not a proxy for task success (two seeds with identical loss curves differed by
-34 points in success at 10k steps), and 50-episode evaluations cannot rank neighbouring checkpoints.
+Two things the per-checkpoint evaluations showed (details in the GitHub README): the training loss did
+not predict task success (two seeds with identical loss curves differed by 34 points in success at 10k
+steps), and 50-episode evaluations cannot rank neighbouring checkpoints.
 
 ## How to use