Update README.md

README.md

@@ -9,8 +9,10 @@ datasets:
 
 # SNet-T25
 SNet-T25 is an MLIP trained on the Titan25 dataset.
-
-Full details of the model architecture and hyperparameters are available at [GAIA paper](https://arxiv.org/abs/2509.25798)
+It was designed for general chemical reactivity, including interfacial reactions,
+and trained on the eleven elements included in Titan25 (C, H, N, O, Ag, Au, Cu, Pd, Pt, Rh, Ru).
+Detailed evaluation results are available at [GAIA paper](https://arxiv.org/abs/2509.25798),
+which also provides full details of the model architecture and hyperparameters.
 
 The original SNet-T25 was trained using our in-house framework;
 we provide a converted version that can be directly used with [the SevenNet framework](https://github.com/MDIL-SNU/SevenNet).