DATASET·Hugging Face·CC-BY-4.0
Calibration Scorecards (Hugging Face)
Monthly Brier + log-loss breakdowns for Kalshi + Polymarket
Monthly rollups of calibration metrics computed off settled-markets. Each month provides:
- Mean Brier + mean log-loss (overall)
- Per-venue (Kalshi vs Polymarket) breakdowns
- Per-category (macro, geo, crypto, event, policy, ...) breakdowns
- 10-bucket calibration histogram (actual resolution rate vs predicted probability)
Published with a 14-day delay after month-end to capture late resolutions. Good benchmark for any probabilistic forecaster.
Tags
datasethuggingfacecalibrationbrierscorecards
Related
- DATASET·CC-BY-4.0Settled Markets (Hugging Face)Monthly partitions of every settled Kalshi + Polymarket market with outcome + predicted price
- DATASET·CC-BY-4.0Calibration Scorecards (Kaggle mirror)Monthly calibration rollups on Kaggle
- DATASET·CC-BY-4.0World Awareness Bench (Hugging Face)Monthly 100-question AI-agent benchmark graded against market consensus