preliminary-evidence wording

README.md

@@ -41,9 +41,10 @@ loadable with LeRobot.
 | 200 (data-rich) | 29% | 29% | 0 pts |
 | 100 (data-scarce) | 8% | **19%** | **+11 pts** |
 
-At 200 demos regularization buys nothing; at 100 demos it lifts success **8% → 19% (+11 pts, ~2.4×)**.
-Regularization buys sample-efficiency **when demonstrations are scarce** — as hypothesized (inspired by
-Konwoo et al. on data-constrained pre-training).
+**Preliminary evidence** suggests that, under a 100-demo budget, enhanced regularization improves PushT
+success from **8% to 19% (+11 pts)**, while showing **no gain at 200 demos** (29% = 29%). This is consistent
+with regularization helping most when demonstrations are scarce (inspired by Konwoo et al. on data-constrained
+pre-training). Single seed — a strong signal, not yet a settled claim.
 
 ## Training