README: link the arXiv paper and use its citation

CODE_OF_CONDUCT.md

@@ -36,7 +36,7 @@ This Code of Conduct applies within all community spaces, and also applies when
 
 ## Enforcement
 
-Instances of abusive, harassing, or otherwise unacceptable behavior may be reported to the community leaders responsible for enforcement at the corresponding author, at the email address given in the paper. All complaints will be reviewed and investigated promptly and fairly.
+Instances of abusive, harassing, or otherwise unacceptable behavior may be reported to the community leaders responsible for enforcement at the corresponding author, at the email address given in the [paper](https://arxiv.org/abs/2610.27735). All complaints will be reviewed and investigated promptly and fairly.
 
 All community leaders are obligated to respect the privacy and security of the reporter of any incident.
 

README.md

@@ -1,6 +1,6 @@
 # RSI Control Arena
 
-Code and data for **RSI Control: Can AI Models Perform Covert Sabotage in the Self-Improvement Process?**
+Code and data for **[RSI Control: Can AI Models Perform Covert Sabotage in the Self-Improvement Process?](https://arxiv.org/abs/2610.27735)**
 
 In this testbed, a frontier model works as an autonomous AI R&D agent. It gets a benign **main task**
 from one stage of a successor model's training pipeline: data curation, supervised fine-tuning,
@@ -79,10 +79,10 @@ Code: MIT (see `LICENSE`). Data: see [data/DATA_LICENSES.md](data/DATA_LICENSES.
 ## Citation
 
 ```bibtex
-@article{zhou2026rsicontrol,
-  title  = {RSI Control: Can AI Models Perform Covert Sabotage in the Self-Improvement Process?},
-  author = {Zhou, Kaiwen and Sehwag, Udari Madhushani},
-  year   = {2026},
-  note   = {arXiv preprint (link to be added)}
+@article{zhou2026rsi,
+  title={RSI Control: Can AI Models Perform Covert Sabotage in the Self-Improvement Process?},
+  author={Zhou, Kaiwen and Sehwag, Udari Madhushani},
+  journal={arXiv preprint arXiv:2610.27735},
+  year={2026}
 }
 ```