Hi, this PR improves the model card by:
- Updating the `pipeline_tag` to `other` to better reflect the multi-task nature of the benchmarking framework (occupancy, spread, retrieval, and regression) described in the paper.
- Adding a link to the official research paper page on Hugging Face: [Does Your Wildfire Prediction Model Actually Work, or Just Score Well?](https://huggingface.co/papers/2605.18911).