Verifiable Rewards for Calibrated Probabilistic Forecasting

Summary

arXiv:2607.00164v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards can in principle train calibrated probabilistic forecasters, since a proper scoring rule such as the Brier score is computed from outcomes alone and is minimized in expectation by the true probability. In practice it degrades calibration, and existing remedies address epistemic uncertainty, where a model's confidence accompanies a verifiably correct or incorrect answer. We study aleatoric forecasting,

SpinGraph analysis pending — check back after processing.

• How to Allocate Your Tokens? Scaling Laws with Training Steps and Batch Size
• Class-Grouped Normalized Momentum and Faster Hyperparameter Exploration to Tackle Class Imbalance in Federated Learning
• Token Geometry
• Geometry-Aware R-Structured Kolmogorov-Arnold Networks
• On the Utility and Factual Reliability of Pruned Mixture-of-Experts Models in the Biomedical Domain
• Conditional Inference Trees and Forests for Feature Selection