TY - JOUR AU - Neyman, Eric AU - Roughgarden, Tim PY - 2022/06/28 Y2 - 2024/03/28 TI - Strictly Proper Contract Functions Can Be Arbitrage-Free JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 36 IS - 5 SE - AAAI Technical Track on Game Theory and Economic Paradigms DO - 10.1609/aaai.v36i5.20449 UR - https://ojs.aaai.org/index.php/AAAI/article/view/20449 SP - 5150-5155 AB - We consider mechanisms for truthfully eliciting probabilistic predictions from a group of experts. The standard approach --- using a proper scoring rule to separately reward each expert --- is not robust to collusion: experts may collude to misreport their beliefs in a way that guarantees them a larger total reward no matter the eventual outcome. It is a long-standing open question whether there is a truthful elicitation mechanism that makes any such collusion (also called "arbitrage") impossible. We resolve this question positively, exhibiting a class of strictly proper arbitrage-free contract functions. These contract functions have two parts: one ensures that the total reward of a coalition of experts depends only on the average of their reports; the other ensures that changing this average report hurts the experts under at least one outcome. ER -