测试大脑和语言模型中的两态访问：人类EEG复现、模拟审计及提出的模型检测方法
The Cross-Substrate Access Assay: What an Indicator Test Must Declare to Travel from Brain to Language Model
- Stellenbosch University（斯泰伦博斯大学）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
本文通过复现EEG两态测试和模拟审计语言模型表示测试，验证全局工作空间理论的两态访问预测，并提出了未运行的模型检测方案。
中文摘要 AI 辅助
大脑和人工神经网络的硬件都是由普通物质组织的，而人工系统的组织能否支持意识仍是一个开放问题。本文通过全局神经元工作空间理论的一个预测，考察了一种提出的机制——对容量有限的全局工作空间的访问：在阈值附近，单次试验的响应分布是两种状态的混合，而非连续体。本文报告了两项已完成的分析。首先，作者使用其代码在二十名参与者的公开EEG数据上复现了已发表的竞争模型测试。在主动会话中，两态模型的受保护超越概率在相同的315毫秒窗口首次超过0.95，每次试验具有约0.003纳特的适度预测优势，且区间边缘对优化器敏感；在被动会话中，一项额外分析显示，分级比较器排名最高，但没有跨窗口的决策。其次，为将测试迁移到语言模型表示而提出的留出族比较，在模拟中于一层进行了校准：在十二种分级零假设下的12,000个数据集中，它没有做出任何错误的两态判定，但其概念簇区间在六种设置下覆盖不足，低至0.22，因此在任何确认性使用之前，必须验证替代区间。提出的模型研究，包括自然文本证据剂量、目标桥梁和状态条件因果测试，已明确但未运行。本文未对体验做出任何声称。
英文摘要
Testing an artificial system for a property linked to consciousness means applying a measurement developed on brains to a system that is not one. Such a transfer must re-examine five parts of the procedure: the competing statistical models, how they are fitted, the unit the inference generalizes over, the quantity the uncertainty interval is about, and the rule that turns a result into a verdict. The Cross-Substrate Access Assay declares all five. Because brain and model signals share no physical scale, every model is scored by the cross-entropy it assigns to held-out data, in nats per trial. The test case is the global neuronal workspace theory, which predicts that near threshold a stimulus either enters a capacity-limited workspace or does not, so that single-trial responses form a mixture of two states. A published test of this prediction on twenty people's electroencephalograms partly reproduces in a re-implementation: the first crossing and the broad ordering over time match, the window-by-window agreement does not. On 12,000 synthetic datasets generated with a single graded state, all of them members of the families the procedure fits and none within 0.0067 nat per trial of the decision boundary, the two models of that test carried over unchanged reported two states in 989 and the expanded families in none; on 600 datasets carrying a mixture the expanded procedure reported two states in 599. Its nominal 95% interval contained the procedure's mean result less often than the required 90% at six of twelve graded settings. No claim about experience is made.
