A verifiable empirical win rate reward combined with gradient masking enables RL training of a 7B model to reach betting-market calibration on NFL win probabilities using only outcome data.
Brill, Ronald Yurko, and Abraham J
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Verifiable Rewards for Calibrated Probabilistic Forecasting
A verifiable empirical win rate reward combined with gradient masking enables RL training of a 7B model to reach betting-market calibration on NFL win probabilities using only outcome data.