Update README.md

README.md

@@ -11,7 +11,7 @@ base_model: meta-llama/Llama-3.2-3B-Instruct
 <p align="center">
   <a href="https://docs.inference.net/use-cases/json-extraction"><strong>Documentation</strong></a> ·
   <a href="https://inference.net/models/schematron-3b"><strong>Serverless API</strong></a> ·
-  <a href="https://openai.com/index/introducing-gpt-oss/"><strong>Announcement blog</strong></a>
+  <a href="https://inference.net/blog/Schematron"><strong>Announcement blog</strong></a>
 </p>
 
 <br>
@@ -68,7 +68,7 @@ We evaluated Schematron's real-world impact on LLM factuality using SimpleQA.
 3. **Structured Extraction**: Schematron extracts JSON data from retrieved pages using the schema
 4. **Answer Synthesis**: Primary LLM produces final answer from structured data
 
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/6626a246891c75742bd19aaf/h2CA0TpQ1hKDxexGlpdSQ.png)
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6626a246891c75742bd19aaf/mU_01IPsf0FvkXYNYstRZ.png)
 
 **Key findings:**
 - Web search paired with JSON extraction improves factuality: Adding Schematron with web retrieval improves GPT-5 Nano's accuracy from 8.54% to 82.87%—nearly a 10x improvement