Calibration and transfer in indicator-based assessments of artificial consciousness

Florentin Koch

cs.AIMar 29, 2026

Calibration and transfer in indicator-based assessments of artificial consciousness

Authors: Florentin Koch

Organizations: École Polytechnique, Institut Polytechnique de Paris, 91120 Palaiseau, France

Abstract

Research on artificial consciousness increasingly shifts evaluation from behaviour to internal architecture. Theory-based indicators are used to update probability assignments. This improves on behavioural tests but raises two distinct problems. First, these assignments cannot currently be calibrated against independently established artificial consciousness outcomes. Second, their evidential relevance is transferred from biological cases without independent support that indicator-consciousness relations remain stable across substrates. This commentary distinguishes calibration from transfer and adapts the iterative natural-kind strategy by proposing a preliminary, theory-relative comparative space for cross-substrate assessment.

Machine Consciousness

Machine consciousness studies whether artificial systems could have subjective experience and how that possibility might be assessed.

See all 20 papers

From cacophony to hierarchy: a principled framework for assessing AI consciousness
Sep 28, 2026Shamil Chandaria, Arvo Muñoz Morán, Fernando Rosas +11Machine Consciousness
Google DeepMind, DeepMind Institute · Flourishing Intelligence Program, Centre for Eudaimonia and Human Flourishing, Linacre College, University of Oxford · Institute of Philosophy, University of London +14
What Can Analogy Tell Us About Artificial Consciousness?
Oct 1, 2026Keith J. Holyoak, Martin M. MontiAnalogical Reasoning Machine Consciousness
Department of Psychology, University of California, Los Angeles · Brain Injury Research Center, Department of Neurosurgery, University of California, Los Angeles
Revisiting Classic Thought Experiments to Measure Consciousness for Artificial Intelligence Safety
Apr 14, 2026Peter David FaganMachine Consciousness
School of Informatics, University of Edinburgh

Sep 28, 2026J/K move · Enter open · S save

From cacophony to hierarchy: a principled framework for assessing AI consciousness

Shamil Chandaria, Arvo Muñoz Morán, Fernando Rosas, Anil Seth+10

Google DeepMind, DeepMind Institute · Flourishing Intelligence Program, Centre for Eudaimonia and Human Flourishing, Linacre College, University of Oxford · Institute of Philosophy, University of London+14

Machine Consciousness

Open paper AskPDF arXiv

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 cacophony of competing theories that often talk past each other. Separating the hard problem from the mapping problem allows the deepest metaphysical disagreements to be set aside: granting that experience supervenes on a system's organisation, the tractable question becomes at which grain of description that supervenience base sits. We extend Marr's three levels of analysis into a five-level hierarchy of functional descriptions (behavioural, computational, intrinsic causal-structural, organismic, and organism-environment) grounded in supervenience, coarse-graining, and multiple realisability. The major theories of consciousness are positioned within this hierarchy according to which level they take to be critical, and for each level we develop operationalisable indicators and assess current AI systems against them. A Bayesian model then combines theoretical credences with indicator evidence into an overall credence in a system's capacity for consciousness. In illustrative assessments, the verdict for current LLMs is driven as much by where theoretical credence is placed as by how the evidence is read: under different stipulated readings and credence distributions, assessments range from below 0.01 to roughly 0.8, showing sensitivity to assumptions. Finally, the consciousness indicators at each level closely overlap with the architectural features needed for general intelligence, suggesting that increasingly capable AI may become a stronger candidate for consciousness. The framework supports a structured agnosticism, in which theoretical commitments are made explicit, credences are updated as evidence accumulates, and assessments take the form of aggregated probabilities rather than verdicts.

Abstract

Machine Consciousness

Explore similar work

From cacophony to hierarchy: a principled framework for assessing AI consciousness

What Can Analogy Tell Us About Artificial Consciousness?

Revisiting Classic Thought Experiments to Measure Consciousness for Artificial Intelligence Safety