Update README.md
Browse files
README.md
CHANGED
|
@@ -33,9 +33,9 @@ We introduce the Open Proof Corpus (OPC)—the world’s first large-scale, open
|
|
| 33 |
Leverage OPC to tackle pressing research questions in automated proof generation:
|
| 34 |
(1) How do natural language and formal proof generation compare?
|
| 35 |
(2) How often do models that produce correct final answers truly reason their way to valid proofs?
|
| 36 |
-
(3) By what margin do best-of-n selection methods
|
| 37 |
|
| 38 |
-
Building on this breakthrough resource, we present **OPC-R1-8B** - an open-source model for proof correctness judging that matches state-of-the-art performance. OPC-R1-8B
|
| 39 |
|
| 40 |
## Introduction
|
| 41 |
|
|
|
|
| 33 |
Leverage OPC to tackle pressing research questions in automated proof generation:
|
| 34 |
(1) How do natural language and formal proof generation compare?
|
| 35 |
(2) How often do models that produce correct final answers truly reason their way to valid proofs?
|
| 36 |
+
(3) By what margin do best-of-n selection methods improve proof quality?
|
| 37 |
|
| 38 |
+
Building on this breakthrough resource, we present **OPC-R1-8B** - an open-source model for proof correctness judging that matches state-of-the-art performance. OPC-R1-8B outperforms the majority of leading closed-source models, reaching an impressive 88.1% accuracy on verifying LLM-generated proofs.
|
| 39 |
|
| 40 |
## Introduction
|
| 41 |
|