A Bayesian Mirror Architecture for Emergent Consciousness: Circular Hierarchies, Self-Manifolds, and Hybrid Event-Self Binding

Computer Science > Machine Learning arXiv:2610.08792 (cs) [Submitted on 22 Feb 2026] Title: A Bayesian Mirror Architecture for Emergent Consciousness: Circular Hierarchies, Self-Manifolds, and Hybrid Event-Self Binding Authors: Eduardo Righi Capanema de Almeida.

计算机科学 > 机器学习 arXiv:2610.08792 (cs) [提交于 2026 年 2 月 22 日] 标题：一种用于涌现意识的贝叶斯镜像架构：循环层级、自流形与混合事件-自我绑定 作者：Eduardo Righi Capanema de Almeida。

Abstract: We present a foundational formulation of the Bayesian Mirror Architecture (BMA), a self-referential generative framework in which sensory abstractions, meta-abstractions, and a self-latent interact through circular recursion. The defining constraint is a closed update S_t <- H_{t-1}, where a hybrid event-self latent H_t binds self-representations to abstract world models and reinjects this coupling into the self-state.

摘要：我们提出了一种贝叶斯镜像架构（BMA）的基础表述，这是一个自指的生成式框架，其中感官抽象、元抽象和自我潜变量通过循环递归进行交互。其定义的约束是一个闭合更新 S_t <- H_{t-1}，其中混合事件-自我潜变量 H_t 将自我表征与抽象世界模型绑定，并将这种耦合重新注入到自我状态中。

Consciousness, in a restricted sense, is not an optimization objective nor a semantic label, but an architectural property of systems possessing this circular structure. Because inference operates over posterior beliefs, BMA’s intrinsic state space is a space of probability measures equipped with optimal-transport geometry.

在受限意义上，意识既不是优化目标，也不是语义标签，而是拥有这种循环结构的系统的一种架构属性。由于推理是在后验信念上进行的，BMA 的内在状态空间是一个配备了最优传输几何的概率测度空间。

Stability and coherence are formulated in the 2-Wasserstein metric on P_2, yielding coordinate-free notions of self-stability and hybrid coherence along belief trajectories. We define a Causal Learning Regime (CLR) via bounds on Wasserstein belief drift together with an integration index capturing sustained coupling between self and world latents.

稳定性和相干性是在 P_2 上的 2-Wasserstein 度量中表述的，从而产生了沿信念轨迹的自稳定性与混合相干性的无坐标概念。我们通过 Wasserstein 信念漂移的界限以及捕捉自我与世界潜变量之间持续耦合的整合指数，定义了一种因果学习机制（CLR）。

CLR diagnoses whether the environment contains learnable causal structure; it is not a marker of consciousness. Global strict contractivity is not required: BMA may exhibit multiple coherent basins. We define self-manifolds basin-wise as supports of invariant measures under local Wasserstein contractivity.

CLR 用于诊断环境是否包含可学习的因果结构；它并非意识的标志。不需要全局严格收缩性：BMA 可能表现出多个相干盆地。我们按盆地定义自流形，即局部 Wasserstein 收缩下不变测度的支撑集。

We identify Wasserstein epsilon-necks, transport bottlenecks where basins decouple, yielding a unique realized continuation in a vanishing-conductance limit. We interpret this selection as choice: internally determined yet externally unpredictable at finite resolution. Learning proceeds via variational free-energy minimization, with stability and agency emerging from what the environment affords to learn.

我们识别出 Wasserstein ε-颈部，即盆地解耦的传输瓶颈，在消失电导极限下产生唯一的实现延续。我们将这种选择解释为抉择：在有限分辨率下，它是内部决定的，但外部不可预测。学习通过变分自由能最小化进行，稳定性和主体性从环境所提供的学习内容中涌现。