1# Raw & processed data — never committed (see data/raw/README.md for provenance)2data/raw/*3!data/raw/README.md4data/processed/*5!data/processed/.gitkeep6!data/processed/category_audit_sample.csv7!data/processed/match_validation_sample.csv8!data/processed/category_train_sample.csv9!data/processed/category_audit_disagreements.csv10!data/processed/match_validation_disagreements.csv11data/processed_model/121314# Python15__pycache__/16*.pyc17.pytest_cache/18.venv/19*.egg-info/2021# LaTeX build artifacts (paper/main.pdf IS committed)22paper/*.aux23paper/*.log24paper/*.out25paper/*.toc26paper/*.lof27paper/*.lot28paper/*.fls29paper/*.fdb_latexmk30paper/*.bbl31paper/*.blg32paper/*.spl33paper/*.synctex.gz34paper/*.run.xml35paper/*.bcf3637# Logs (ledger and output manifest ARE committed)38logs/*39!logs/run_ledger.jsonl40!logs/manifest.json41!logs/model_inventory.json4243# macOS44.DS_Store45logs/*.log46data/interim/*47!data/interim/.gitkeep48.env49*.db50*.db-wal51*.db-shm52paper/tex2docx/5354# large external downloads (rebuild with src/ingest/external.py; manifest + derived CSVs are committed)55data/external/dl/56data/external/geo/57