New data sources: NASA APOD, GBIF biodiversity, Open-Meteo climate,
solar flares, USGS rivers, arXiv papers, NOAA ocean buoys, disease
tracking, air quality, 126 asteroid close approaches, NASA natural
events (wildfires), and cross-domain correlation engine.
Also adds train-discoveries crate for RuVector-based cross-domain
similarity search training pipeline.
https://claude.ai/code/session_01UWE22wnsZRSHKhT4h4Axby