__pycache__/
*.py[cod]
*.egg-info/
.eggs/
dist/
build/
.venv/
venv/
env/
.env
*.log
.DS_Store
.ipynb_checkpoints/
.jupyter/
# IDE directories
.vscode/
.idea/
*.suo
*.user
*.swp
*.swo

# AI agent working directories
.claude/
.codex/
.cursor/
.aider/
.aider.chat.history.md
.continue/
.windsurf/
.gemini/
.codeium/

# Raw scraped/downloaded files
data/raw/*.pdf
research/downloaded_papers/
research/raw_pdfs/
nohup.out

# Generated notebook outputs
data/processed/*.png
data/processed/*.svg

# Bulk data directories (too large for git, not curated)
data/cache/
data/raw/crawled/
data/raw/excluded/
data/raw/brin_multistation_raw/
data/raw/bsrn/
data/raw/tess/
data/raw/gan_mn/
data/raw/washetdonker/
data/raw/globe_at_night/
data/raw/surfrad/
data/raw/galicia_night_sky/
data/raw/india_twilight_photometer/
data/raw/madrid_sqm_evol/
data/raw/majadahonda_sqm_2019/

# Collection session logs and scratch
data/raw/collection_log*.txt
data/raw/sources_crawled.md

# Research scratch files (superseded by aggregate_d0_values.csv)
research/aggregate_d0_database.csv
research/aggregate_analysis.md
research/candidate_papers.json
research/mine_*.py

# Experimental collection scripts (not part of core pipeline)
src/autonomous_collect.py
src/compute_aggregate_times.py
src/collect/aladhan.py
src/collect/autonomous_collector.py
src/collect/aggregate_to_records.py
src/collect/bulk_generator.py
src/collect/bulk_runner.py
src/collect/cities.py
src/collect/collect_agent.py
src/collect/harvest.py
src/collect/jakim.py
src/collect/morocco.py
src/collect/muis_singapore.py
src/collect/openalex_harvester.py
src/collect/source_tracker.py
src/collect/waktusolat.py
src/collect/web_harvester.py
.vscode/*