Cite the arXiv paper (2610.20951)

README.md

@@ -20,10 +20,10 @@ tags:
 [![System 1.5](https://img.shields.io/badge/System_1.5-Decision_Model-2847E8?style=flat-square)](https://openlair.github.io/lev/)
 ![Native depths](https://img.shields.io/badge/Native_depths-1--2-2847E8?style=flat-square)
 [![Apache 2.0](https://img.shields.io/badge/License-Apache_2.0-596268?style=flat-square)](LICENSE)
-[![Paper on alphaXiv](https://img.shields.io/badge/Paper-alphaXiv-B31B1B?style=flat-square)](https://www.alphaxiv.org/pdf/2610.lev-looped-decision-models)
+[![arXiv](https://img.shields.io/badge/arXiv-2610.20951-B31B1B?style=flat-square)](https://arxiv.org/abs/2610.20951)
 [![Code on GitHub](https://img.shields.io/badge/Code-GitHub-181717?style=flat-square&logo=github)](https://github.com/OpenLAIR/lev)
 
-**[Project](https://openlair.github.io/lev/) · [Paper on alphaXiv](https://www.alphaxiv.org/pdf/2610.lev-looped-decision-models) · [PDF](https://openlair.github.io/lev/assets/lev-paper.pdf) · [GitHub](https://github.com/OpenLAIR/lev) · [Models & data](https://huggingface.co/collections/songdj/lev)**
+**[Project](https://openlair.github.io/lev/) · [Paper on arXiv](https://arxiv.org/abs/2610.20951) · [PDF](https://arxiv.org/pdf/2610.20951) · [GitHub](https://github.com/OpenLAIR/lev) · [Models & data](https://huggingface.co/collections/songdj/lev)**
 
 **One checkpoint. Multiple depths. A probability for every option.**
 Lev gives text decisions an adjustable compute budget: reuse the same recurrent weights, then read the shared decision head at the chosen depth. It returns typed option probabilities without decoding a chain of reasoning.
@@ -123,14 +123,16 @@ The base card at the pinned revision is the provenance for these statements; no
 
 **Lev: Thinking Fast and Deep with Looped Decision Models** — Dingjie Song, Zhiling Yan, Yuxuan Zhang, and Lichao Sun.
 
-Read the paper on [alphaXiv](https://www.alphaxiv.org/pdf/2610.lev-looped-decision-models) or download the [PDF](https://openlair.github.io/lev/assets/lev-paper.pdf); the arXiv identifier will be added when it is announced. Code is on [GitHub](https://github.com/OpenLAIR/lev) and the research overview is on the [project page](https://openlair.github.io/lev/).
+Read the paper on [arXiv](https://arxiv.org/abs/2610.20951) ([PDF](https://arxiv.org/pdf/2610.20951)) or discuss it on [alphaXiv](https://www.alphaxiv.org/abs/2610.20951). Code is on [GitHub](https://github.com/OpenLAIR/lev) and the research overview is on the [project page](https://openlair.github.io/lev/).
 
 ```bibtex
-@misc{song2026lev,
-  title        = {Lev: Thinking Fast and Deep with Looped Decision Models},
-  author       = {Song, Dingjie and Yan, Zhiling and Zhang, Yuxuan and Sun, Lichao},
-  year         = {2026},
-  howpublished = {alphaXiv},
-  url          = {https://www.alphaxiv.org/abs/2610.lev-looped-decision-models}
+@misc{song2026levthinkingfastdeep,
+      title={LEV: Thinking Fast and Deep with Looped Decision Models},
+      author={Dingjie Song and Zhiling Yan and Yuxuan Zhang and Lichao Sun},
+      year={2026},
+      eprint={2610.20951},
+      archivePrefix={arXiv},
+      primaryClass={cs.AI},
+      url={https://arxiv.org/abs/2610.20951},
 }
 ```