Doc: update DPA3 reference (#4781)

<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

- **Documentation**
- Updated user documentation and README to reflect support for both
DPA-2 and DPA-3 models.
- Added references to the DPA-3 model paper in the documentation and
class descriptions for improved citation and clarity.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->

Author: iProzd

README.md

@@ -76,7 +76,7 @@ See [our v2 paper](https://doi.org/10.1063/5.0155600) for details of all feature
 #### v3
 
 - Multiple backends supported. Add PyTorch and JAX backends.
-- The DPA-2 model.
+- The DPA-2 and DPA-3 models.
 - Plugin mechanisms for external models.
 
 See [our v3 paper](https://doi.org/10.1021/acs.jctc.5c00340) for details of all features until v3.0.

deepmd/dpmodel/descriptor/dpa3.py

@@ -251,7 +251,7 @@ def deserialize(cls, data: dict) -> "RepFlowArgs":
 
 @BaseDescriptor.register("dpa3")
 class DescrptDPA3(NativeOP, BaseDescriptor):
-    r"""The DPA-3 descriptor.
+    r"""The DPA-3 descriptor[1]_.
 
     Parameters
     ----------
@@ -282,6 +282,12 @@ class DescrptDPA3(NativeOP, BaseDescriptor):
         When True, local indexing and mapping are applied to neighbor lists and embeddings during descriptor computation.
     type_map : list[str], Optional
         A list of strings. Give the name to each type of atoms.
+
+    References
+    ----------
+    .. [1] Zhang, D., Peng, A., Cai, C. et al. Graph neural
+       network model for the era of large atomistic models.
+       arXiv preprint arXiv:2506.01686 (2025).
     """
 
     def __init__(

deepmd/pd/model/descriptor/dpa3.py

@@ -63,7 +63,7 @@
 
 @BaseDescriptor.register("dpa3")
 class DescrptDPA3(BaseDescriptor, paddle.nn.Layer):
-    r"""The DPA-3 descriptor.
+    r"""The DPA-3 descriptor[1]_.
 
     Parameters
     ----------
@@ -94,6 +94,12 @@ class DescrptDPA3(BaseDescriptor, paddle.nn.Layer):
         Not supported yet in Paddle.
     type_map : list[str], Optional
         A list of strings. Give the name to each type of atoms.
+
+    References
+    ----------
+    .. [1] Zhang, D., Peng, A., Cai, C. et al. Graph neural
+       network model for the era of large atomistic models.
+       arXiv preprint arXiv:2506.01686 (2025).
     """
 
     def __init__(

deepmd/pt/model/descriptor/dpa3.py

@@ -63,7 +63,7 @@
 
 @BaseDescriptor.register("dpa3")
 class DescrptDPA3(BaseDescriptor, torch.nn.Module):
-    r"""The DPA-3 descriptor.
+    r"""The DPA-3 descriptor[1]_.
 
     Parameters
     ----------
@@ -94,6 +94,12 @@ class DescrptDPA3(BaseDescriptor, torch.nn.Module):
         When True, local indexing and mapping are applied to neighbor lists and embeddings during descriptor computation.
     type_map : list[str], Optional
         A list of strings. Give the name to each type of atoms.
+
+    References
+    ----------
+    .. [1] Zhang, D., Peng, A., Cai, C. et al. Graph neural
+       network model for the era of large atomistic models.
+       arXiv preprint arXiv:2506.01686 (2025).
     """
 
     def __init__(

doc/model/dpa3.md

@@ -11,7 +11,7 @@ Its model design ensures exceptional fitting accuracy and robust generalization
 Furthermore, DPA-3 maintains energy conservation and respects the physical symmetries of the potential energy surface,
 making it a dependable tool for a wide range of scientific applications.
 
-Reference: will be released soon.
+Reference: [DPA-3 paper](https://arxiv.org/abs/2506.01686).
 
 Training example: `examples/water/dpa3/input_torch.json`.