1000×1000 collection releases 133 dynamical processes, from chaos to brains and climate
burny_tech · x · 2026-10-01
The compTimeSeries team introduced the "1000×1000 collection": 1000 simulated time series × 1000 samples spanning 133 dynamical processes, ranging from noise and chaos to hearts, brains, and climate.
The dataset is designed to let researchers systematically benchmark time-series models against diverse dynamical structures, and the authors invite the community to explore it.
More from Research
- Researcher teases 'interp exponential': wave of interpretability papers coming in weeks — burny_tech · 2026-10-01
- DerivAudit: 17-21% of long-term agent memories unsupported by interaction history — newyorkuniversity · 2026-10-01
- VoxParity benchmark: only 11 of 23 voice agents act on what they hear, not just read — Bhavik Mangla · 2026-10-01
- CASCADE filters genetic variants through four questions; the 3% that pass are twice as GWAS-enriched — anshulkundaje · 2026-10-01
- Nature paper: 10M-cell immune multiome atlas from 1,108 FinnGen donors links disease variants to regulation — anshulkundaje · 2026-10-01
- Duplicate repost of the same Nature immune multiome atlas paper — anshulkundaje · 2026-10-01