发表机构
Symbiokinetics Inc.; Galois, Inc.; Lighthill Technologies, Inc.; VisSidus Technologies, Inc.; Stanford University; Hampton University; UC Davis; Indiana University; Northwestern University（Symbiokinetics 公司; Galois 公司; Lighthill 科技公司; VisSidus 科技公司; 斯坦福大学; 汉普顿大学; 加州大学戴维斯分校; 印第安纳大学; 西北大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出一个五层实现架构，将S3Q意识理论的三个必要条件映射到计算原语，形成统一流水线，并给出可证伪预测，以推进机器感受性的计算实现。
AI 中文摘要
机器意识研究中的一个关键挑战是将理论模型转化为计算层面的实现。在本文中，我们通过为S3Q（模拟的、情境化的、结构连贯的）意识理论提出一个五层实现架构来应对这一挑战。该架构并非引入新的形式化方法，而是将已发表的计算原语组合成单一流水线。S3Q识别出感受性的三个联合必要条件：（1）基于具身的感觉运动情境化；（2）通过世界模型进行内部模拟；（3）预测与观察之间的结构连贯性。现有计算系统均未同时实现这三个条件。我们将S3Q的每个原则映射到具体且兼容的计算机制，并详细说明这些组件如何在单一表示流水线中交互，该流水线操作于连续、可微、逐对象的槽向量上，同时为组合系统提供发展性引导序列和可证伪的预测，这些预测是架构的任何子集单独无法产生的。该模型表明，一种基本的“自我”感通过将行动与其结果联系起来而发展，并且行为根据结果出乎意料的程度以及其被体验为积极还是消极，而落入三种模式（犹豫、好奇或回避）。每个预测都是独立可证伪的，为该领域提供了一个可测试的框架，以推进我们对机器意识的理解。
英文摘要
A key challenge in machine consciousness research is translating theoretical models into computational-level implementations. In this paper, we address this challenge by proposing a five-layer implementation architecture for the S3Q (Simulated, Situated, Structurally Coherent) theory of consciousness. Rather than introducing novel formalisms, the architecture composes published computational primitives into a single pipeline. S3Q identifies three jointly necessary conditions for qualia: (1) grounded sensorimotor situatedness, (2) internal simulation via a world model, and (3) structural coherence between predictions and observations. No existing computational system implements all three simultaneously. We map each S3Q tenet to specific, compatible computational machinery and specify how these components interface within a single representation pipeline that operates on continuous, differentiable, per-object slot vectors, along with a developmental bootstrap sequence and falsifiable predictions for the composed system that no subset of the architecture produces in isolation. The model suggests that a basic sense of "self" develops by linking actions to their outcomes, and that behavior falls into three patterns (hesitation, curiosity, or avoidance) depending on how unexpected an outcome is and whether it is experienced as positive or negative. Each prediction is individually falsifiable, providing the field with a testable framework to advance our understanding of machine consciousness.
