发表机构
Carnegie Mellon University; Zhejiang University（卡内基梅隆大学; 浙江大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究指出价格水平审计天生对特定算法合谋盲目，通过理论分析、语言模型智能体实验及以太坊拍卖数据验证，提出监管应转向竞价身份计数而非检测。
AI 中文摘要
算法合谋的实证研究仅针对数据提出一个问题：价格是否超竞争？我们证明，存在一种合谋行为可给出“否”的答案，却仍能获利。考虑仅通过未解释竞价成分的联合分布耦合的竞价智能体，每个智能体自身的竞价法则恰好保持在竞争水平。对于输入为单个智能体价格或竞价历史的任何测试，其功效恰好等于假阳性率，且该结论适用于直至共单调性的所有耦合强度。因此，已发表的检测方法因天生设计而非功效不足对该合谋行为盲目，且无法通过增加样本量修复。由此得到三项实证结果：第一，该机制存在于真实的语言模型智能体中：19家独立开发者的20个模型，每个模型3个部署提示，某一模型两次部署间的残差相关性为+0.053，而不同模型间为+0.0001，在能查看所有订单特征且采用样本外拟合的审计器下，按开发者聚类的95%置信区间为[0.030, 0.078]；第二，耦合程度随采样温度升高单调下降（p=0.002），这将一个部署参数转化为潜在的缓解措施；第三，在涵盖39个竞价者的77684次竞价、共24天的以太坊区块构建拍卖数据中，诚实竞价者对群体本身存在高度依赖，使得假阳性率为5%的筛查阈值需高于+0.50至+0.81，这是家族式抽样阈值的20至32倍，且不会随审计窗口增大而降低。由于合法多身份操作与合谋在行为上无法区分，可处理的监管目标并非检测而是计数：将40个竞价身份解析为23个运营商使赫芬达尔指数提升247.5%，而从公开竞价流中添加行为聚类后提升至324.5%。
英文摘要
Empirical work on algorithmic collusion asks one question of the data: are prices supracompetitive? We show this can be answered "no" by a conspiracy that is nonetheless profitable. Consider bidding agents that couple only through the joint distribution of their unexplained bid components, leaving every agent's own bid law exactly at the competitive law. Any test whose input is a single agent's price or bid history then has power exactly equal to its false-positive rate, for every coupling strength up to comonotonicity. The published detection methodology is therefore blind to this conduct by construction rather than underpowered, and no sample size repairs it. Three empirical results follow. First, the mechanism appears in real language-model agents: twenty models from nineteen independent developers, three deployment prompts each, show residual correlation of $+0.053$ between two deployments of one model against $+0.0001$ across models, with a 95% interval clustered by developer of $[0.030, 0.078]$, under an auditor that sees every order feature and is fitted out of sample. Second, the coupling falls monotonically as sampling temperature rises ($p=0.002$), turning a deployment parameter into a candidate mitigation. Third, on 24 days of Ethereum block-building auction data covering 77,684 bids from 39 bidders, the honest population of bidder pairs is itself so dependent that a screen held at a 5% false-positive rate must sit above a floor of $+0.50$ to $+0.81$, which is 20 to 32 times the family-wise sampling threshold and does not fall as the audit window grows. Since lawful multi-identity operation and conspiracy are behaviourally indistinguishable here, the tractable regulatory target is not detection but counting: resolving 40 bidding identities into 23 operators raises the Herfindahl index by 247.5%, and adding behavioural clusters from public bid streams reaches 324.5%.
Comments11 pages, 4 figures, includes technical appendix
