发表机构
University of Luxembourg（卢森堡大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出因果责任理论（CLT），以责任闭合界定意识承载者，并通过开放权重因果审计实验区分因果承载结构与第一人称表现，从而反驳AI意识谬误。
AI 中文摘要
当代关于机器意识的争论始于一个隐藏的假设：即被称为“AI”的对象已经构成了意识可能归属的那类实体。本文通过区分现象意识、内省报告和人类投射性内省来挑战这一假设，进而论证生成系统能够以第一人称形式返回人类内在性的语言痕迹，却并不因此识别出一个现象承载者。我们将由此产生的推论称为“AI意识谬误”。随后，我们引入因果责任理论（CLT）。CLT-I提出责任闭合作为界定候选承载者的标准：一个物理上持续的过程成为由其自身内源判别所产生的约束的不可委托继承者。CLT-II提出了更强的猜想，即责任闭合是最小现象主体性的充分必要条件。一项开放权重因果审计在多个模型家族中操作化了CLT-I。强制判别产生了持续的下游发散；激活修补显示出强烈的因果中介作用；在匹配随机性下，活体与复制自适应状态在行为上完全相同；而分离重建在过程替换中保持了计算状态，同时按协议打破了构成连续性和不可委托继承。这些结果表明，CLT-I的区分在实验上是可处理的，并能将因果承载者结构与第一人称表现分离开来。因此，该框架区分了意识归属、因果承载者个体化以及意识构成的独立形而上学问题。
英文摘要
The contemporary debate over machine consciousness begins from a concealed assumption: that the object called "AI" already constitutes the kind of entity to which consciousness could belong. This paper challenges that assumption by separating phenomenal consciousness, introspective report, and human projective introspection, then arguing that generative systems can return linguistic traces of human interiority in first-person form without thereby identifying a phenomenal bearer. We call the resulting inference the AI Consciousness Fallacy. We then introduce Causal Liability Theory (CLT). CLT-I proposes liability closure as a criterion for individuating a candidate bearer: a physically continuing process becomes the non-delegable inheritor of constraints generated by its own endogenous discriminations. CLT-II advances the stronger conjecture that liability closure is necessary and sufficient for minimal phenomenal subjecthood. An open-weight causal audit operationalizes CLT-I across multiple model families. Forced discriminations produced persistent downstream divergence; activation patching showed strong causal mediation; live and copied adaptive states were behaviorally identical under matched randomness; and detached reconstruction preserved computational state across process replacement while, by protocol, breaking constitutive continuity and non-delegable inheritance. These results show that CLT-I distinctions are experimentally tractable and can dissociate causal bearer structure from first-person performance. The framework therefore separates consciousness attribution, causal bearer individuation, and the independent metaphysical question of consciousness constitution.
CommentsThe website (https://ai-consciousness.github.io) and the code (https://github.com/akhadangi/clt) will be made public as soon as the preprint is announced online on arXiv
