Sausage5464 commited on
Commit
4c4ffd6
·
verified ·
1 Parent(s): 1661cab

Update index.html

Browse files
Files changed (1) hide show
  1. index.html +3 -4
index.html CHANGED
@@ -162,11 +162,10 @@
162
  </div>
163
 
164
  <script type="text/markdown" id="md-source">
165
-
166
-
167
  ## What StatProver Does
168
 
169
- StatProver provides a structured workflow for automated proof generation and self-correction, helping users transform a statistical proposition or source document into a complete LaTeX proof.
170
 
171
  <video width="100%" autoplay loop muted playsinline>
172
  <source src="https://raw.githubusercontent.com/StatAI-Lab/StatProver_doc/main/videos/demo.mp4" type="video/mp4">
@@ -214,7 +213,7 @@ StatProver retrieves reference cases from a database of **40,366** research-leve
214
 
215
  **Contribution 2. Data-Driven Snippet-Level Self-Correction**
216
 
217
- StatProver also uses a large empirical fault repository containing over **80,000** error snippets, constructed from LLM failure trajectories on StatEval’s research-level data. This repository supports fine-grained diagnosis and targeted correction, allowing the system to identify subtle logical gaps and proof errors beyond standard self-reflection.
218
 
219
  **Contribution 3. Interactive Proof Assistant Platform**
220
 
 
162
  </div>
163
 
164
  <script type="text/markdown" id="md-source">
165
+
 
166
  ## What StatProver Does
167
 
168
+ StatProver provides a structured workflow for automated proof generation and self-correction, helping users transform a statistical proposition or source document into a complete LaTeX proof. Built on the comprehensive statistical reasoning benchmark **[StatEval](https://stateval.github.io/)**, StatProver retrieves relevant references to refine proof skeletons and performs self-correction by learning from the strategies and details of similar theoretical proofs.
169
 
170
  <video width="100%" autoplay loop muted playsinline>
171
  <source src="https://raw.githubusercontent.com/StatAI-Lab/StatProver_doc/main/videos/demo.mp4" type="video/mp4">
 
213
 
214
  **Contribution 2. Data-Driven Snippet-Level Self-Correction**
215
 
216
+ StatProver also uses a large empirical fault repository containing over **80,000** error snippets, constructed from LLM failure trajectories on **[StatEval’s](https://stateval.github.io/)** research-level data. This repository supports fine-grained diagnosis and targeted correction, allowing the system to identify subtle logical gaps and proof errors beyond standard self-reflection.
217
 
218
  **Contribution 3. Interactive Proof Assistant Platform**
219