Hi! This PR improves the model card for `roberta-sentence-classifier` by:
- Adding the `pipeline_tag: text-classification` to the YAML metadata.
- Linking the model card to the paper [Cognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty Prediction](https://huggingface.co/papers/2606.28186).
- Linking to the official GitHub repository [c-steve-wang/Epi2Diff](https://github.com/c-steve-wang/Epi2Diff).
- Describing the 8 cognitive problem-solving episodes that this model is fine-tuned to classify.
