mirror of
https://github.com/open-thought/reasoning-gym.git
synced 2026-04-19 12:58:07 +00:00
49b1dbbcce
The prompt asked to "find the length of the shortest path" but the expected answer is a sequence of directions. This caused models to answer with a number instead of directions, degrading evaluation results. Closes #522 Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
54 lines
443 B
Text
54 lines
443 B
Text
.aider*
|
|
.env
|
|
# Python
|
|
__pycache__/
|
|
*.py[cod]
|
|
*$py.class
|
|
*.so
|
|
.Python
|
|
build/
|
|
develop-eggs/
|
|
dist/
|
|
downloads/
|
|
eggs/
|
|
.eggs/
|
|
lib/
|
|
lib64/
|
|
parts/
|
|
sdist/
|
|
var/
|
|
wheels/
|
|
*.egg-info/
|
|
.installed.cfg
|
|
*.egg
|
|
.python-version
|
|
|
|
# Virtual Environment
|
|
venv/
|
|
env/
|
|
ENV/
|
|
|
|
# IDE
|
|
.idea/
|
|
.vscode/
|
|
*.swp
|
|
*.swo
|
|
|
|
# Testing
|
|
.coverage
|
|
htmlcov/
|
|
.pytest_cache/
|
|
|
|
# OSX
|
|
.DS_Store
|
|
|
|
# Jupyter Notebook
|
|
.ipynb_checkpoints/
|
|
.virtual_documents/
|
|
|
|
# logs
|
|
wandb/
|
|
outputs/
|
|
*.log
|
|
|
|
uv.lock
|