# ---- Large / derived data (reproducible via build_rdf_dataset.py) ----
# Raw prospectus prose fetched from EDGAR (GBs)
data/rdf_poc/prose/
# Generated training samples and splits (embed raw SEC text, 100s of MB)
data/rdf_poc/samples.jsonl
data/rdf_poc/train.jsonl
data/rdf_poc/val.jsonl
data/rdf_poc/test.jsonl
# Raw SEC bulk downloads (re-downloadable from sec.gov)
data/ncen/
data/nport/
data/xbrl_rr/

# SQLite working DB
fund_data.db
fund_data.db-shm
fund_data.db-wal

# Archives
*.zip

# Python
__pycache__/
*.pyc
*.pyo

# LaTeX build artifacts
*.aux
*.log
*.out
*.toc
*.fls
*.fdb_latexmk
*.synctex.gz

# OS / editor
.DS_Store
.claude/