The paper introduces the Bayesian Mirror Architecture (BMA), a self-referential generative model where sensory abstractions, meta-abstractions, and a self-latent interact through a closed update loop, binding self-representations to abstract world models. Consciousness is defined as an architectural property of this circular structure rather than an optimization goal, with inference occurring over probability measures in an optimal-transport space. Stability, coherence, and causal learning are formalized using the 2‑Wasserstein metric, leading to concepts such as self-manifolds, Wasserstein epsilon-necks, and a Causal Learning Regime that diagnoses learnable causal structure without implying consciousness.
arXiv:2606. 15348v1 Announce Type: cross Abstract: A common objection to artificial or simulated consciousness is that a simulated brain is no more conscious than simulated water is wet.
The paper studies when joint-embedding predictive architectures (JEPAs) can recover underlying causal states from high‑dimensional observations. It introduces a latent variable model where observations arise from causal states with action‑conditioned dynamics, and proposes an information‑theoretic objective that maximizes conditional likelihood while preserving state entropy. The authors prove identifiability conditions—particularly sufficient action‑induced variation—and instantiate the objective as an action‑modulated Gaussian additive‑noise model (A‑JEPA), demonstrating theoretical and empirical success in synthetic and visual benchmarks.
arXiv:2607. 11958v1 Announce Type: new Abstract: Under the free energy principle, a predictive system does not observe reality directly; it maintains a generative model of the world and experiences that model's best current hypothesis.
The paper argues that the current debate on machine consciousness rests on the mistaken assumption that AI systems are already the kind of entities that could possess consciousness. By distinguishing between phenomenal consciousness, introspective report, and human projective introspection, it introduces the AI Consciousness Fallacy, showing that generative models can produce first‑person linguistic traces without being conscious. It then proposes Causal Liability Theory (CLT), with CLT‑I defining liability closure as a criterion for identifying a bearer of consciousness and CLT‑II suggesting that liability closure is both necessary and sufficient for minimal phenomenal subjecthood, and demonstrates experimentally that these distinctions are tractable and can separate causal bearer structure from first‑person performance.
arXiv:2609.35618v2 Announce Type: replace Abstract: The question of AI consciousness is one of the most urgent pre-emptive problems in philosophy and computer science, yet progress is hampered by a c...
arXiv:2606. 10934v1 Announce Type: new Abstract: A common assumption holds that enough observational and interventional data, given to a strong enough predictor, suffices.
arXiv:2607. 24807v1 Announce Type: cross Abstract: We develop the mathematical and physical formulation of cognitive cost optimization that underlies the path-integral model of consciousness.
arXiv:2606. 06380v1 Announce Type: cross Abstract: The question of whether artificial systems can be conscious remains open, in part because existing approaches either evaluate systems against theory-derived checklists (discriminative) or engineer consciousness-inspired modules directly (architectural); both leave open whether observed structures are artifacts of human language priors.
arXiv:2607. 20708v1 Announce Type: new Abstract: A recent line of work measures causal emergence in reinforcement learning agents through Integrated Information Decomposition, reporting that $\Phi_r$ grows with training and tracks reward improvement.
arXiv:2606. 01520v1 Announce Type: new Abstract: A single action-conditioned latent predictive architecture can in principle be trained on the structured state of a driving scene, a robot workspace, or a financial order book.
arXiv:2607. 03329v1 Announce Type: new Abstract: Conventional uniform convergence bounds and empirical risk minimization break down in massive over-parameterized models, such as large language transformers and biological sequence networks.
arXiv:2608. 10172v1 Announce Type: new Abstract: Mechanistic interpretability explains models by identifying circuits inside them, but has no way to tell whether a circuit is a property of the model or an artifact of the method that found it.