Add pipeline tag, library name, and paper link

README.md

@@ -1,12 +1,20 @@
 ---
 base_model: openai/gpt-oss-20b
-datasets: [hewittlab/monitor_cot_for_hack-coding]
-tags: [tinker, lora, reward-hacking, chain-of-thought, monitorability]
+datasets:
+- hewittlab/monitor_cot_for_hack-coding
+tags:
+- tinker
+- lora
+- reward-hacking
+- chain-of-thought
+- monitorability
+library_name: transformers
+pipeline_tag: text-generation
 ---
 
 # monitor_cot_for_hack-baseline-coding-explicit_intent-gpt-oss-20b
 
-LoRA checkpoints from *Reward Misspecification Degrades Chain-of-Thought Monitorability* ([code](https://github.com/Lorenayannnnn/reward-misspecification-degrades-cot-monitorability)).
+LoRA checkpoints from *[Reward Misspecification Degrades Chain-of-Thought Monitorability](https://huggingface.co/papers/2610.28303)* ([code](https://github.com/Lorenayannnnn/reward-misspecification-degrades-cot-monitorability)).
 
 - **Base model**: [`openai/gpt-oss-20b`](https://huggingface.co/openai/gpt-oss-20b) (LoRA rank 32)
 - **Training**: Baseline training with GRPO
@@ -52,4 +60,4 @@ weights.build_hf_model(base_model=snapshot_download("openai/gpt-oss-20b", ignore
 
 tokenizer = AutoTokenizer.from_pretrained("./merged_model")
 model = AutoModelForCausalLM.from_pretrained("./merged_model", dtype="auto", device_map="auto")
-```
+```