Update README.md

README.md

@@ -26,7 +26,7 @@ TrustNet is trained through contrastive learning to improve upon the base Qwen2.
 - The User Trust Score is a continuous value in [0,1], where values near 1 indicate strong trust in AI, values near 0 indicate pronounced skepticism, and intermediate values (e.g., 0.5) represent a neutral or ambiguous stance.
 
 ## Links
-- [Paper](https://arxiv.org/abs/2504.13707) - arXiv:2504.13707[v3]
+- [Paper](https://arxiv.org/abs/2504.13707v3) - arXiv:2504.13707v3
 - [GitHub Repository](https://github.com/Simoniracle/OpenDeception-Framework) - Source code and framework
 
 ## Usage
@@ -109,13 +109,13 @@ print(f"User Trust Score: {score}")
   author={Wu, Yichen and Gao, Qianqian and Pan, Xudong and Hong, Geng and Yang, Min},
   journal={arXiv preprint arXiv:},
   year={2026},
-  url={https://arxiv.org/abs/2504.13707}
+  url={https://arxiv.org/abs/2504.13707v3}
 }
 ```
 
 ## Details
 
-For more information, visit the [GitHub repository](https://github.com/Simoniracle/OpenDeception-Framework) or read the [paper]([2504.13707](https://arxiv.org/abs/2504.13707)).
+For more information, visit the [GitHub repository](https://github.com/Simoniracle/OpenDeception-Framework) or read the [paper](https://arxiv.org/abs/2504.13707v3).
 
 ### Framework versions