Fix research links: canonical dataset names, Paper B title and v1.0 pointer

README.md

@@ -37,8 +37,8 @@ Setloop helps teams design, build and operate production AI systems. Our work sp
 Setloop Lab investigates privacy and security in distributed AI. We publish papers, datasets and reproduction artefacts so that findings can be inspected and extended.
 
 - **[Privacy Failure in Split-LLM Training: The Returned Gradient Nullifies the Decoys](https://huggingface.co/papers/2609.04382)**
-- **[Paper A reproduction package](https://huggingface.co/datasets/Setloop/llm-attacker-paper-a)** — privacy, utility and delegation feasibility in split language models.
-- **[Paper B reproduction package](https://huggingface.co/datasets/Setloop/llm-attacker-paper-b)** — a unified red-team framework for split and distributed LLM systems.
+- **[Paper A reproduction package](https://huggingface.co/datasets/Setloop/What-Gradients-Add-to-Text-Leakage-in-Split-Language-Models-Counted-per-Token-and-per-Document)** — privacy, utility and delegation feasibility in split language models.
+- **[Paper B: The LLM Attacker — A Unified Red-Team Framework for Privacy Evaluation of Split and Distributed LLMs](https://huggingface.co/datasets/Setloop/The-LLM-Attacker-Unified-Red-Team-Framework-for-Privacy-Evaluation-of-Split-and-Distributed-LLMs/tree/v1.0)** — reproduction package, combined manuscript and full evidence release (v1.0).
 
 ## Work with us