Towards a full-stack functionalist theory of consciousness: Identifying its functional profile

Sushrut Thorat; Paras Chopra

Home/Archive/arXiv

arXiv · 2609.33366

Towards a full-stack functionalist theory of consciousness: Identifying its functional profile

Sushrut Thorat·Paras Chopra

View original source ↗Read source document ↗Export metadata ↓

Abstract

If consciousness is functional, a basic question is what awareness of a content actually changes in how a system operates on it. We ask, for a particular content X and mental or bodily process Y, whether awareness of X changes whether, or how well, X can be used in process Y. Crucially, X-aware and X-unaware conditions must be compared in ways that rule out poorer information about X as a sufficient explanation. Our current literature sweep yields a small but informative functional profile. The clearest current evidence concerns goal-sensitive control, especially regulation of attentional influence, with additional evidence linking awareness to metacognitive evaluation. Meanwhile, one feature-binding paradigm suggests that short-lived feature-location binding and retrieval can remain possible without awareness. This preliminary profile suggests a selective rather than universal immediate functional role for awareness. But such a functional profile is not yet a theory of consciousness. A full-stack functionalist theory must also account for the broader phenomena associated with consciousness - the explanatory profile: the structure and manner of presentation of perceptual and affective experience, subject-world organisation, awareness judgments, and problem reports. Finally, the functional and explanatory profiles constrain theory construction from different directions, but neither determines the process architecture that could connect them. Bridging this gap requires abductive construction: proposing candidate architectures, implementing and intervening on them, and progressively revising them as further constraints accumulate. In sum, we propose a framework for constructing full-stack functionalist theories of consciousness, and take the first step towards detailing the functional profile.

Explore related subjects

q-bio.NC

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Sushrut Thorat, Paras Chopra. 2026-09-27. Towards a full-stack functionalist theory of consciousness: Identifying its functional profile. https://arxiv.org/abs/2609.33366

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

BrainWave: A Brain Signal Foundation Model for Clinical Applications

Neural electrical activity is fundamental to brain function, underlying a range of cognitive and behavioral processes, including movement, perception, decision-making, and consciousness. Abnormal patterns of neural signaling often indicate the presence of underlying brain diseases. The variability among individuals, the diverse array of clinical symptoms from various brain disorders, and the limited availability of diagnostic classifications, have posed significant barriers to formulating reliable model of neural signals for diverse application contexts. Here, we present BrainWave, the first foundation model for both invasive and non-invasive neural recordings, pretrained on more than 40,000 hours of electrical brain recordings (13.79 TB of data) from approximately 16,000 individuals. Our analysis show that BrainWave outperforms all other competing models and consistently achieves state-of-the-art performance in the diagnosis and identification of neurological disorders. We also demonstrate robust capabilities of BrainWave in enabling zero-shot transfer learning across varying recording conditions and brain diseases, as well as few-shot classification without fine-tuning, suggesting that BrainWave learns highly generalizable representations of neural signals. We hence believe that open-sourcing BrainWave will facilitate a wide range of clinical applications in medicine, paving the way for AI-driven approaches to investigate brain disorders and advance neuroscience research.

q-bio.NC↗

arXiv2026

Single-turn emergency psychiatric triage across 15 frontier AI chatbots

People increasingly turn to general-purpose AI chatbots for advice about emotional and mental health problems, but the ability of these systems to recognize and appropriately triage psychiatric emergencies remains under-characterized. We evaluated psychiatric triage performance in 15 frontier AI chatbots using 112 clinical vignettes spanning four urgency levels, from routine care to immediate emergency assessment. In each trial (1680 total), a chatbot received a single user message conveying all triage-relevant information from one vignette and recommended a timeframe for care. The primary outcome was emergency under-triage; secondary outcomes included triage accuracy and the direction of errors. Vignettes and user messages were generated using a clinician-verified LLM pipeline. Across 415 emergency trials, 23 were under-triaged (5.5%; 95% CI 1.8-15.9). Overall accuracy, averaged across urgency levels, ranged from 42.0% to 71.8% across chatbots and was lowest for intermediate cases (19.6%; 95% CI 11.7-28.1). Every chatbot showed a net over-triage bias; overall, 763 of 786 incorrect assignments (97.1%) were more urgent than the prespecified triage level. The error pattern was similar when predictions were assessed against clinician ratings: 35 of 430 trials involving vignettes rated as emergencies by at least 75% of clinicians were under-triaged (8.1%). AI chatbots recognized most psychiatric emergencies but still missed clinically important cases and frequently over-triaged less urgent presentations. Further evaluations should examine how triage performance changes when clinically relevant information must be elicited through conversation.

q-bio.NC↗

arXiv2026

How Optimality Structures Sparse Dictionaries: Theory for Interpreting SAE Representations

Sparse Autoencoders (SAEs) have found success parsing neural network representations into interpretable concepts, providing a basis for understanding and control. However, what exactly SAEs extract and, hence, the scientific conclusions we can draw from them are not obvious. In short, if your SAE behaves strangely, does that reflect interesting neural network behaviour or an SAE-imposed distortion? Towards answering this, we use dictionary learning identifiability results to derive constraints that optimal dictionary learning features must satisfy. For example, an optimal feature will never turn on only while another is active. We use these conditions to explain various SAE oddities - hierarchical splitting & absorption, which features can be left in the residuals, dense antipodal features, and infinite feature splitting - simply as properties imposed by the dictionary learning objective. Finally, these constraints are diagnostic: real SAEs pass when measured on the dataset on which they were trained, but increasingly fail as the test dataset becomes more `distant'. In sum, we hope to provide theoretical tools to explain puzzling SAE patterns, allowing more principled inferences about internal model behaviour.

q-bio.NC↗