# Joint Scoring Rules: Zero-Sum Competition Avoids Performative Prediction

arXiv: https://arxiv.org/abs/2412.20732 · HTML: https://mlsanity.com/paper/2412.20732/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 30 references that are in the map.
- First posted on arXiv 30 Dec 2024.

## Builds on (most cited first, 12 of 12)

- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Performative Prediction](https://mlsanity.com/paper/2002.06673/) (2020)
- [Risks from Learned Optimization in Advanced Machine Learning Systems](https://mlsanity.com/paper/1906.01820/) (2019)
- [Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals](https://mlsanity.com/paper/2210.01790/) (2022)
- [Optimal Policies Tend to Seek Power](https://mlsanity.com/paper/1912.01683/) (2019)
- [Hidden Incentives for Auto-Induced Distributional Shift](https://mlsanity.com/paper/2009.09153/) (2020)
- [On Second-Order Scoring Rules for Epistemic Uncertainty Quantification](https://mlsanity.com/paper/2301.12736/) (2023)
- [Natural Selection Favors AIs over Humans](https://mlsanity.com/paper/2303.16200/) (2023)
- [Good and safe uses of AI Oracles](https://mlsanity.com/paper/1711.05541/) (2017)
- [Conditioning Predictive Models: Risks and Strategies](https://mlsanity.com/paper/2302.00805/) (2023)
- [Incentivizing honest performative predictions with proper scoring rules](https://mlsanity.com/paper/2305.17601/) (2023)
- [Scoring Rules for Performative Binary Prediction](https://mlsanity.com/paper/2207.02847/) (2022)

## Built on by (most cited first, 1 of 1)

- [The Endogeneity of Miscalibration: Impossibility and Escape in Scored Reporting](https://mlsanity.com/paper/2605.07671/) (2026)

## Abstract (arXiv)

In a decision-making scenario, a principal could use conditional predictions from an expert agent to inform their choice. However, this approach would introduce a fundamental conflict of interest. An agent optimizing for predictive accuracy is incentivized to manipulate their principal towards more predictable actions, which prevents that principal from being able to deterministically select their true preference. We demonstrate that this impossibility result can be overcome through the joint evaluation of multiple agents. When agents are made to engage in zero-sum competition, their incentive to influence the action taken is eliminated, and the principal can identify and take the action they most prefer. We further prove that this zero-sum setup is unique, efficiently implementable, and applicable under stochastic choice. Experiments in a toy environment demonstrate that training on a zero-sum objective significantly enhances both predictive accuracy and principal utility, and can eliminate previously learned manipulative behavior.