# Future-as-Label: Scalable Supervision from Real-World Outcomes

arXiv: https://arxiv.org/abs/2601.06336 · HTML: https://mlsanity.com/paper/2601.06336/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 6 references that are in the map.
- First posted on arXiv 9 Jan 2026.

## Builds on (most cited first, 5 of 5)

- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs](https://mlsanity.com/paper/2506.14245/) (2025)
- [Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains](https://mlsanity.com/paper/2503.23829/) (2025)
- [CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward](https://mlsanity.com/paper/2508.03686/) (2025)
- [Outcome-based Reinforcement Learning to Predict the Future](https://mlsanity.com/paper/2505.17989/) (2025)

## Built on by (most cited first, 11 of 11)

- [Agentic Forecasting using Sequential Bayesian Updating of Linguistic Beliefs](https://mlsanity.com/paper/2604.18576/) (2026)
- [Aligning LLMs with Human Uncertainty: A Beta-Bernoulli Calibrator for LLM Forecasting](https://mlsanity.com/paper/2605.27668/) (2026)
- [Foresight Learning for SEC Risk Prediction](https://mlsanity.com/paper/2601.19189/) (2026)
- [Forecasting Supply Chain Disruptions with Foresight Learning](https://mlsanity.com/paper/2604.01298/) (2026)
- [Harnessing Pre-Resolution Signals for Future Prediction Agents](https://mlsanity.com/paper/2604.15719/) (2026)
- [Training Large Language Models to Predict Clinical Events](https://mlsanity.com/paper/2605.12817/) (2026)
- [Distilling Temporal Search and Reasoning: Evolving LLMs for Future Prediction via Harness-Assisted Efficient Data Synthesis](https://mlsanity.com/paper/2607.25554/) (2026)
- [How Proper Scoring Rules Shape LLM Forecasting](https://mlsanity.com/paper/2608.28482/) (2026)
- [CruxBench: A Benchmark of Information Discovery](https://mlsanity.com/paper/2609.35879/) (2026)
- [CHAIN: Calibrated LLM Forecasting via Causal-Temporal Hypergraph Inference](https://mlsanity.com/paper/2609.36689/) (2026)
- [Can Language Models Learn to Forecast Stock Prices](https://mlsanity.com/paper/2609.36914/) (2026)

## Abstract (arXiv)

Time creates free supervision: forecasts about real-world events resolve to verifiable outcomes. The passage of time provides labels that require no annotation. To exploit this structure, we extend reinforcement learning with verifiable rewards to real-world prediction over time. We train language models to make probabilistic forecasts from causally masked information, using proper scoring rules as the reward function once events resolve. Learning is driven entirely by realized outcomes, enabling scalable outcome-based supervision in open-world prediction. On real-world forecasting benchmarks, Qwen3-32B trained using Foresight Learning improves Brier score by 27% and halves calibration error relative to its pretrained baseline, and outperforms Qwen3-235B on both constructed future-event prediction tasks and the Metaculus benchmark despite a 7x parameter disadvantage.