Added paper

Author: adaamko

README.md

@@ -326,11 +326,14 @@ python scripts/build_full_dataset.py \
 ## Citation
 
 ```bibtex
-@software{kovacs2026squeez,
-    title={Squeez: Compressing Tool Output for LLM Coding Agents},
-    author={Adam Kovacs},
-    year={2026},
-    url={https://github.com/KRLabsOrg/squeez}
+@misc{kovács2026squeeztaskconditionedtooloutputpruning,
+      title={Squeez: Task-Conditioned Tool-Output Pruning for Coding Agents}, 
+      author={Ádám Kovács},
+      year={2026},
+      eprint={2604.04979},
+      archivePrefix={arXiv},
+      primaryClass={cs.SE},
+      url={https://arxiv.org/abs/2604.04979}, 
 }
 ```
 

blog/huggingface_blogpost.md

@@ -246,6 +246,7 @@ One recurring bottleneck in coding agents is deciding what to keep from a single
 
 ## Resources
 
+- **Paper:** [arXiv:2604.04979](https://arxiv.org/abs/2604.04979)
 - **Model:** [KRLabsOrg/squeez-2b](https://huggingface.co/KRLabsOrg/squeez-2b) (Apache 2.0)
 - **Dataset:** [KRLabsOrg/tool-output-extraction-swebench](https://huggingface.co/datasets/KRLabsOrg/tool-output-extraction-swebench) (Apache 2.0)
 - **Code & CLI:** [github.com/KRLabsOrg/squeez](https://github.com/KRLabsOrg/squeez) (Apache 2.0)