Add `pipeline_tag: text-classification` and improve link visibility

This PR improves the model card for `adaptive-classifier/chayan` by making the following updates:

- **Adds `pipeline_tag: text-classification` to the metadata**: This ensures better discoverability on the Hugging Face Hub, allowing users to find this LLM router when filtering by the text classification pipeline.
- **Enhances link visibility**: Key links to the associated paper (Hugging Face and arXiv), the model's library code, and the RouterArena project page are moved to a prominent position at the top of the model card for easier access and improved readability. The original "Links" section at the bottom is removed to avoid redundancy.

README.md

@@ -1,5 +1,11 @@
 ---
+language:
+- en
 library_name: adaptive-classifier
+license: apache-2.0
+metrics:
+- accuracy
+pipeline_tag: text-classification
 tags:
 - llm
 - routing
@@ -7,30 +13,32 @@ tags:
 - bert
 - router-arena
 - model-selection
-language:
-- en
-metrics:
-- accuracy
-license: apache-2.0
 ---
 
 # Chayan: Multi-Model LLM Router
 
-**Chayan** is a high-performance LLM router that intelligently routes between 4 models (gpt-4o-mini, gemini-2.5-flash-lite, gemini-2.5-flash, and gpt-4o) to optimize the accuracy-cost tradeoff.
+This model is a high-performance LLM router presented in the paper [RouterArena: An Open Platform for Comprehensive Comparison of LLM Routers](https://huggingface.co/papers/2510.00202).
+
+-   📚 Paper (Hugging Face): [RouterArena: An Open Platform for Comprehensive Comparison of LLM Routers](https://huggingface.co/papers/2510.00202)
+-   📚 Paper (arXiv): https://arxiv.org/abs/2510.00202
+-   💻 Library Code: https://github.com/codelion/adaptive-classifier
+-   🌐 RouterArena Project Page: https://routeworks.github.io/
+
+**Chayan** intelligently routes between 4 models (gpt-4o-mini, gemini-2.5-flash-lite, gemini-2.5-flash, and gpt-4o) to optimize the accuracy-cost tradeoff.
 
 ## 🏆 RouterArena Performance
 
 **Official Leaderboard Results** (8,400 queries):
-- 🥇 **#1 Optimal Accuracy Score: 88.7%** - SOTA! (Best routing decision quality)
-- 🥈 **#2 Optimal Selection Score: 43.0%** - Silver! (Second-best model selection)
-- **#7 Overall** (#5 open-source): 64.9% accuracy, 63.8 arena score
-- **$0.60 per 1K queries** - Cost-efficient routing
+-   🥇 **#1 Optimal Accuracy Score: 88.7%** - SOTA! (Best routing decision quality)
+-   🥈 **#2 Optimal Selection Score: 43.0%** - Silver! (Second-best model selection)
+-   **#7 Overall** (#5 open-source): 64.9% accuracy, 63.8 arena score
+-   **$0.60 per 1K queries** - Cost-efficient routing
 
 ![RouterArena Leaderboard](routerarena_leaderboard.png)
 
 **What do these metrics mean?**
-- **Optimal Accuracy**: When Chayan routes to a model, that model gives the correct answer 88.7% of the time
-- **Optimal Selection**: Chayan selects the best available model 43% of the time
+-   **Optimal Accuracy**: When Chayan routes to a model, that model gives the correct answer 88.7% of the time
+-   **Optimal Selection**: Chayan selects the best available model 43% of the time
 
 View full leaderboard: [RouterArena](https://routeworks.github.io/) | [PR #24](https://github.com/RouteWorks/RouterArena/pull/24)
 
@@ -73,9 +81,9 @@ selected_model = max(calibrated_scores.items(), key=lambda x: x[1])[0]
 ## Architecture
 
 **Core Components:**
-- **Base Model**: BERT-base-uncased embeddings
-- **Classifier**: Adaptive K-NN with prototype memory (FAISS-backed)
-- **Innovation**: Calibrated confidence scores to correct training data imbalance
+-   **Base Model**: BERT-base-uncased embeddings
+-   **Classifier**: Adaptive K-NN with prototype memory (FAISS-backed)
+-   **Innovation**: Calibrated confidence scores to correct training data imbalance
 
 **Supported Models:**
 
@@ -89,18 +97,18 @@ selected_model = max(calibrated_scores.items(), key=lambda x: x[1])[0]
 ## How It Works
 
 ### Training
-- **Dataset**: RouterArena sub_10 (809 queries)
-- **Oracle Labels**: 4-model cascade strategy (select cheapest successful model)
-- **Training Time**: 19.2 minutes
-- **Method**: K-NN classifier with 3000 prototypes, temperature 0.4
+-   **Dataset**: RouterArena sub_10 (809 queries)
+-   **Oracle Labels**: 4-model cascade strategy (select cheapest successful model)
+-   **Training Time**: 19.2 minutes
+-   **Method**: K-NN classifier with 3000 prototypes, temperature 0.4
 
 ### The Calibration Breakthrough
 
 The uncalibrated router achieved 61.76% accuracy but was biased toward gpt-4o-mini (83% routing). This happened because the training data had class imbalance:
-- 57% gpt-4o-mini examples
-- 27% gpt-4o examples
-- 12% gemini-flash-lite examples
-- 4% gemini-flash examples
+-   57% gpt-4o-mini examples
+-   27% gpt-4o examples
+-   12% gemini-flash-lite examples
+-   4% gemini-flash examples
 
 **Solution**: Apply post-training calibration factors to correct the bias without retraining.
 
@@ -121,10 +129,10 @@ The uncalibrated router achieved 61.76% accuracy but was biased toward gpt-4o-mi
 **Key Insight**: Chayan achieves 99% of perfect oracle performance at 57% lower cost.
 
 **Full Dataset (8,400 queries):**
-- **Optimal Accuracy**: 88.7% (🥇 #1)
-- **Optimal Selection**: 43.0% (🥈 #2)
-- **Overall Accuracy**: 64.9% (#7 overall, #5 open-source)
-- **Cost**: $0.60/1K queries
+-   **Optimal Accuracy**: 88.7% (🥇 #1)
+-   **Optimal Selection**: 43.0% (🥈 #2)
+-   **Overall Accuracy**: 64.9% (#7 overall, #5 open-source)
+-   **Cost**: $0.60/1K queries
 
 ## Advanced Usage
 
@@ -144,10 +152,10 @@ predictions = router.predict(augmented, k=4)
 
 ## Limitations
 
-- Calibration factors optimized on RouterArena sub_10; may require adjustment for other domains
-- Requires the 4 specific models to be available via API
-- Performance depends on query distribution similar to RouterArena benchmark
-- Cost estimates assume ~500 tokens per query
+-   Calibration factors optimized on RouterArena sub_10; may require adjustment for other domains
+-   Requires the 4 specific models to be available via API
+-   Performance depends on query distribution similar to RouterArena benchmark
+-   Cost estimates assume ~500 tokens per query
 
 ## Citation
 
@@ -159,10 +167,4 @@ predictions = router.predict(augmented, k=4)
   publisher = {GitHub},
   url = {https://github.com/codelion/adaptive-classifier}
 }
-```
-
-## Links
-
-- **Library**: https://github.com/codelion/adaptive-classifier
-- **RouterArena**: https://routeworks.github.io/
-- **RouterArena Paper**: https://arxiv.org/abs/2510.00202
+```