发表机构
Untapped Capital（未开发资本）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究以16个轻量角色条件化GPT-4.1配置面板为对象，发现通过粗略边际检验成本较低，还揭示了p13需复制、无实时调用可验证结果等结论，未证明LLM可替代人类。
AI 中文摘要
大型语言模型正越来越多地被用作合成研究参与者，其有效性通常通过边际响应是否与人类数据相似来验证。我们研究了一个包含16个轻量角色条件化GPT-4.1配置的固定面板，在重复战略博弈中的表现。该面板在4个重复博弈单元中的3个达到了预先注册的宽泛参考条件均值标准；唯一未达标的情况比下限参考界低0.011。变异程度与提示词高度相关，但变异的占比取决于不确定性假设：固定面板对称Dirichlet敏感性分析在Jeffreys alpha=0.5下，提示词间变异的中位数占比为63%-71%，在alpha=1下为47%-53%，而有限机会插件估计的占比为85%-96%。聚合延续概率的对比值为+0.083和+0.078，保守的同时95%置信区间为[-0.171, +0.330]和[-0.181, +0.330]。处理同时改变了延续过程及其文本表征。一项单独的措辞与位置操作使基础配置的合作率从0/40提升至37/40，且标签冲突也揭示了表征控制的存在。原始角色层面的p13结果未进行前瞻性家族控制，而裁决后的精确检验在结构上效力不足；因此p13是复制目标而非既定发现。外部审查揭示了家族误差、依赖性、构念及边界不确定性缺陷，零调用重新分析在不改写历史记录的情况下改变了解释。注册的边际标准可在不精确估计处理-响应对象的情况下通过。一个公开胶囊验证了4916次确认性3-5阶段运行，无实时模型调用。结果仅涉及一个固定的模型-提示词面板，未确立与人类的可替代性。
英文摘要
Large language models are increasingly used as synthetic research participants and are often validated by whether their marginal responses resemble human data. We study a fixed panel of sixteen lightweight persona-conditioned GPT-4.1 configurations in repeated strategic games. The panel met preregistered broad-reference condition-mean criteria in three of four repeated-game cells; the sole miss was 0.011 below the lower reference bound. Variation was strongly prompt-indexed, but its share depended on uncertainty assumptions: fixed-panel symmetric-Dirichlet sensitivities produced median between-prompt shares of 63%-71% under Jeffreys alpha=0.5 and 47%-53% under alpha=1, while finite-opportunity plug-in estimates were 85%-96%. Aggregate continuation-probability contrasts were +0.083 and +0.078, with conservative simultaneous 95% intervals [-0.171, +0.330] and [-0.181, +0.330]. The treatment jointly changed the continuation process and its textual representation. A separate wording-and-position operation shifted cooperation from 0/40 to 37/40 in the bare configuration, and a label conflict also revealed representation control. The original persona-level p13 result was not prospectively family-controlled, while a post-adjudication exact gate was structurally underpowered; p13 is therefore a replication target rather than a finding. External review exposed family-error, dependence, construct, and boundary-uncertainty defects, and zero-call reanalysis changed the interpretation without rewriting the historical record. The registered marginal criteria could be passed without precisely estimating the treatment-response object. A public capsule verifies 4,916 confirmatory Phase 3-5 runs with no live model calls. The results concern one fixed model-prompt panel and do not establish human substitutability.
Comments19 pages, 5 figures. Project site: https://yoheinakajima.github.io/synthetic-players/ ; code, data, registrations, review record, and zero-call replay capsule: https://github.com/yoheinakajima/synthetic-players
