Update app.py

app.py

@@ -471,8 +471,7 @@ def ui() -> gr.Blocks:
                 ### Methodology
                 - **`src_clf`**: Source classification of a fragment.
                 - **`sum_rag`**: RAG-style QA strictly from provided passages. Answers are graded by a judge gpt-4o model on a 0-2 scale; we report F1 score.
-                - **`sum_rag_v2`**: Like `sum_rag` but harder - with longer, augmented contexts and strict deranged negatives built. Same generation and 0-2 judging; we report F1 score.
-                - **`rag_v2`**: Advanced legal reasoning dataset with multiple question types:
+                - **`sum_rag_v2`**: Advanced legal reasoning dataset with multiple question types:
                   - **Contradiction resolution**: Questions about resolving contradictions or ambiguities within legal texts, requiring analysis of conflicting rules or statements
                   - **Legal inference**: Questions testing whether hypothetical situations meet specific legal criteria, requiring identification of legal prerequisites and exceptions
                 """)