Update README.md

README.md

@@ -1,20 +1,20 @@
----
-tags:
-- model_hub_mixin
-- pytorch_model_hub_mixin
-- pytorch
-- statistical_inference
-- mutual_information
-- set_transformer
-license: mit
----
+---
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+- pytorch
+- statistical_inference
+- mutual_information
+- set_transformer
+license: mit
+---
 #
 
 # 🧬 MIST: Mutual Information estimation via Supervised Training
 
 [![Paper](https://img.shields.io/badge/arXiv-Paper-b31b1b?logo=arxiv&logoColor=b31b1b)](https://arxiv.org/pdf/2511.18945)
 [![GitHub Repo](https://img.shields.io/badge/GitHub-Code-FFD700?logo=github)](https://github.com/grgera/mist)
-[![Data](https://img.shields.io/badge/Data-Zenodo-%23009788)](zenodo.org/records/17599669)
+[![Data](https://img.shields.io/badge/Data-Zenodo-%23009788)](https://zenodo.org/records/17599669)
 
 ## Overview
 MIST is a framework for fully data-driven mutual information (MI) estimation. It leverages neural networks trained on large meta-datasets of distributions to learn flexible, differentiable MI estimators that generalize across sample sizes, dimensions, and modalities. The framework supports uncertainty quantification via quantile regression and provides fast, well-calibrated inference suitable for integration into modern ML pipelines.