Add pipeline tag and links to paper and code

Hi! I'm Niels from the Hugging Face community team.

I've opened this PR to improve the model card for this artifact. Specifically, I've:
- Added the `pipeline_tag: text-ranking` to the metadata to improve discoverability.
- Added a link to the associated paper: [Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agents](https://huggingface.co/papers/2606.08151).
- Included a link to the official GitHub repository.
- Maintained the existing technical documentation and code snippets.

This will help users better understand the research context of this adapter and how to use it within the CICL framework.

README.md

@@ -1,7 +1,8 @@
 ---
-library_name: peft
 base_model: Qwen/Qwen3.5-9B
+library_name: peft
 license: apache-2.0
+pipeline_tag: text-ranking
 tags:
 - peft
 - lora
@@ -13,9 +14,11 @@ tags:
 
 # CICL Qwen3.5-9B QLoRA Adapter
 
-This repository contains a PEFT LoRA adapter trained for decision-aware context judgment experiments in CICL. The repository does not include the Qwen3.5-9B base model.
+This repository contains a PEFT LoRA adapter trained for decision-aware context judgment experiments as presented in the paper [Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agents](https://huggingface.co/papers/2606.08151).
+
+Official Code: [XinyuGuan/CICL](https://github.com/stephen-guan-researcher/CICL)
 
-It is an **adapter-only** release. To run it, load the adapter with the matching base model:
+The repository does not include the Qwen3.5-9B base model. It is an **adapter-only** release. To run it, load the adapter with the matching base model:
 
 ```text
 base model: Qwen/Qwen3.5-9B
@@ -100,4 +103,4 @@ These numbers are intended as diagnostic evidence for the paper's surrogate-judg
 - This is not a standalone language model; it requires `Qwen/Qwen3.5-9B`.
 - It is trained for CICL counterfactual context-judgment experiments, not general chat or coding-agent use.
 - It should not be described as equivalent to Claude/Opus teacher models.
-- It is intended to support reproducibility of the surrogate-judge and selection-agreement experiments reported with the CICL project.
+- It is intended to support reproducibility of the surrogate-judge and selection-agreement experiments reported with the CICL project.