__pycache__/
*.py[cod]
*.egg-info/
dist/
build/
.venv/
venv/
.pytest_cache/
.ruff_cache/
results/
cache/
config.json

# Corpus response bodies hold third-party page content: metadata and labels
# are versioned, raw bodies are shared on request (see paper/corpus/README.md).
paper/corpus/*/bodies/
