pith. sign in

arxiv: 2606.06424 · v1 · pith:6USDW6JDnew · submitted 2026-06-04 · 🧬 q-bio.NC

Intrinsic Computational Functionalism: From Observer-Relative Maps to Observer-Independent Structures

Shuqin Ma (1 , 2) , Ryota Kanai (3) ((1) School of Philosophy , Fudan University , Shanghai , China , (2) Sussex Centre for Consciousness Science , University of Sussex
show 4 more authors
United Kingdom (3) Araya Inc. Tokyo Japan)
This is my paper

Pith reviewed 2026-06-27 22:29 UTC · model grok-4.3

classification 🧬 q-bio.NC
keywords computational functionalismobserver relativityintrinsic computationconsciousnessdynamical systemsgrain selectioninterventionstate space structure
0
0 comments X

The pith

Computational properties for consciousness must be identified through dynamics-internal grain selection after empirically disciplined partition choices to avoid observer relativity.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper develops intrinsic computational functionalism, according to which consciousness-relevant computational structures must belong to the system itself rather than depend on external interpretive labels. It introduces two operational criteria: C1 requires the property to be specifiable without observer labelling and invariant under structure-preserving relabellings, while C2 requires it to be grounded in mutually constraining state-space structure exhibited under intervention. The central argumentative device is a three-tier decomposition of how computational properties are identified, separating interpreter-relative label selection (tier i), theoretically constrained partition selection (tier ii), and dynamics-internal grain selection (tier iii). The paper claims that only tier iii, conditional on disciplined tier ii choices, can produce observer-independent structures that survive existing anti-computational objections.

Core claim

Intrinsic computational functionalism holds that if consciousness is computationally constituted, it depends on physically realised computational structures the system possesses in virtue of itself. The argumentative core is the three-tier decomposition of identification work: interpreter-relative label selection (tier i), theoretically constrained partition selection (tier ii), and dynamics-internal grain selection (tier iii). Any computational property capable of avoiding the observer-relativity objection must be identified, if at all, through tier iii dynamics-internal grain selection, conditional on empirically disciplined tier ii choices. Syntax-is-not-semantics arguments, mapmaker argu

What carries the argument

The three-tier decomposition of computational property identification, in which tier iii dynamics-internal grain selection operates on state-space structure whose variables mutually constrain one another and respond to intervention.

If this is right

  • Syntax-is-not-semantics arguments succeed only against computational accounts located at tier i.
  • Mapmaker arguments succeed only against accounts that rely on externally imposed maps at tier i.
  • The observer-relativity component of biological-naturalist objections succeeds only against tier i views.
  • Intrinsic computational functionalism survives the listed objections once the tiers are distinguished.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The tier framework could be used to re-examine existing dynamical models of neural activity by checking whether their grain selections satisfy mutual constraint under intervention.
  • Empirical interventions that alter state-space organisation without changing external labels might provide tests for whether candidate structures meet C2.
  • The approach suggests that neighbouring questions about the physical basis of experience could be narrowed to those computational organisations that survive relabelling invariance.

Load-bearing premise

The two criteria C1 and C2 successfully distinguish observer-independent structures from observer-relative ones.

What would settle it

An example of a structure selected via tier iii dynamics-internal grain selection that nevertheless requires an external observer's choice of labels or partitions to be computationally meaningful would falsify the central claim.

read the original abstract

Anti-computational arguments show that externally imposed computational interpretations cannot ground consciousness, but they do not establish that all computational organisations are observer-relative. We develop intrinsic computational functionalism: the view that, if consciousness is computationally constituted, it depends on physically realised computational structures the system has in virtue of itself rather than on labels imposed by an external interpreter. Two criteria operationalise this view. (C1) System-intrinsic instantiation: the relevant property must be specifiable without an observer's labelling, and invariant under structure-preserving relabellings of the system's variables. (C2) Causal-dynamical organisation under intervention: the property must be grounded in a state-space structure whose variables mutually constrain one another, and whose organisation is exhibited in counterfactual response under intervention. Together these criteria specify what any candidate computational account must satisfy to remain observer-independent, without selecting which intrinsic structures bear on experience. The argumentative core is a three-tier decomposition of identification work: interpreter-relative label selection (tier i), theoretically constrained partition selection (tier ii), and dynamics-internal grain selection (tier iii). We argue that any computational property capable of avoiding the observer-relativity objection must be identified, if at all, through tier (iii) dynamics-internal grain selection, conditional on empirically disciplined tier (ii) choices. Syntax-is-not-semantics arguments, mapmaker arguments, and the observer-relativity component of biological-naturalist objections succeed against views that locate the consciousness-relevant property at tier (i); once the tiers are distinguished, intrinsic computational functionalism survives.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 0 minor

Summary. The paper develops intrinsic computational functionalism, the view that consciousness (if computationally constituted) depends on physically realised computational structures the system possesses intrinsically rather than via external labels. It operationalises this via two criteria—C1 (specifiable without observer labelling and invariant under relabellings) and C2 (grounded in mutually constraining state-space structure exhibited under intervention)—and a three-tier decomposition of identification work (tier i: interpreter-relative label selection; tier ii: theoretically constrained partition selection; tier iii: dynamics-internal grain selection). The central claim is that syntax-is-not-semantics, mapmaker, and biological-naturalist objections succeed only against tier-(i) views, so that any observer-independent computational property must be identified (if at all) at tier (iii) conditional on empirically disciplined tier-(ii) choices.

Significance. If the tier distinction and criteria C1/C2 are shown to demarcate genuinely observer-independent structures, the paper supplies a conceptual framework that could allow computational theories of consciousness to survive observer-relativity objections while remaining physically grounded, thereby clarifying conditions under which functionalist accounts can claim intrinsic status.

major comments (2)
  1. [Criteria C1 and C2 (abstract and argumentative core)] The manuscript does not demonstrate that interventions and counterfactual responses in C2 can be fixed without an external perspective that selects the intervention protocol, admissible perturbations, and relevant variables held fixed. This choice appears to remain open after tier-(ii) constraints, so C2 does not yet guarantee observer-independence at tier (iii). This directly affects the central claim that the criteria block the observer-relativity objection.
  2. [three-tier decomposition (abstract and argumentative core)] The tiers are introduced stipulatively to define the defended view, with no independent argument that they are non-overlapping or that tier-(ii) choices are sufficiently empirically disciplined to constrain tier (iii) without circular dependence on the authors' own stipulations about what counts as 'intrinsic' or 'dynamics-internal'. This bears on whether the decomposition actually rescues the position from the cited objections.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the careful and substantive report. The two major comments raise important questions about the grounding of C2 and the status of the tier decomposition. We respond point by point below and indicate where revisions will be made.

read point-by-point responses

  1. Referee: [Criteria C1 and C2 (abstract and argumentative core)] The manuscript does not demonstrate that interventions and counterfactual responses in C2 can be fixed without an external perspective that selects the intervention protocol, admissible perturbations, and relevant variables held fixed. This choice appears to remain open after tier-(ii) constraints, so C2 does not yet guarantee observer-independence at tier (iii). This directly affects the central claim that the criteria block the observer-relativity objection.

    Authors: We agree that the manuscript would benefit from a more explicit demonstration that tier-(ii) theoretical constraints suffice to fix the intervention protocol and admissible variables. The paper treats tier (ii) as supplying the relevant physical theory (e.g., the dynamical equations or state-space topology of the target system) that determines which perturbations count as interventions and which variables are held fixed. Nevertheless, the current text leaves the precise mechanism of this fixing somewhat implicit. In revision we will add a dedicated paragraph (new subsection 3.2.1) that illustrates, with a concrete dynamical-systems example, how the choice of intervention set is dictated by the theory rather than by an external labeler. This addition will strengthen the claim that C2, once tier (ii) is in place, removes observer-relativity at tier (iii). revision: partial

  2. Referee: [three-tier decomposition (abstract and argumentative core)] The tiers are introduced stipulatively to define the defended view, with no independent argument that they are non-overlapping or that tier-(ii) choices are sufficiently empirically disciplined to constrain tier (iii) without circular dependence on the authors' own stipulations about what counts as 'intrinsic' or 'dynamics-internal'. This bears on whether the decomposition actually rescues the position from the cited objections.

    Authors: The tiers are distinguished by the distinct logical operations performed at each stage: tier (i) assigns arbitrary external labels, tier (ii) applies constraints drawn from an independently motivated physical or neuroscientific theory, and tier (iii) selects grain on the basis of the resulting state-space dynamics alone. Because these operations are defined by what they do rather than by the authors' prior notion of intrinsicality, the decomposition is not circular by construction. We concede, however, that the manuscript does not supply a separate meta-argument showing the tiers are exhaustive and non-overlapping in every possible case. In the revision we will insert a short clarifying paragraph (end of section 2) that derives the three tiers from the standard workflow of computational modeling in neuroscience, thereby providing an independent rationale rather than a purely stipulative one. This will also make explicit how tier-(ii) empirical discipline is sourced from the relevant scientific literature rather than from the authors' definitions. revision: partial

Circularity Check

0 steps flagged

No circularity: criteria and tiers are definitional tools, not reductions of a derivation

full rationale

The paper introduces C1, C2, and the three-tier decomposition explicitly as operationalisations of its proposed view rather than as outputs derived from prior results or data. The central claim—that computational properties avoiding observer-relativity must be identified at tier (iii)—is presented as a consequence of distinguishing the tiers, not as a prediction or first-principles result that reduces by construction to the inputs. No equations, fitted parameters, self-citations, or renamings of known results appear. The structure is self-contained conceptual clarification, which is the normal non-circular case.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

The central claim rests on domain assumptions about the nature of computation and observer-relativity rather than fitted parameters or new physical entities.

axioms (2)
  • domain assumption Consciousness, if computationally constituted, depends on structures the system possesses in virtue of itself.
    Stated in the opening of the abstract as the target of the view.
  • domain assumption Externally imposed computational interpretations cannot ground consciousness.
    Invoked as the starting point from anti-computational arguments.

pith-pipeline@v0.9.1-grok · 5860 in / 1227 out tokens · 25042 ms · 2026-06-27T22:29:45.096838+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

69 extracted references · 23 canonical work pages · 1 internal anchor

  1. [1]

    and Marshall, William and Mayner, William G

    Albantakis, Larissa and Barbosa, Leonardo and Findlay, Graham and Grasso, Matteo and Haun, Andrew M. and Marshall, William and Mayner, William G. P. and Zaeemzadeh, Alireza and Boly, Melanie and Juel, Bj. Integrated information theory (. PLoS Computational Biology , volume=. 2023 , publisher=

    2023

  2. [3]

    Collected Fictions , publisher=

    On exactitude in science , author=. Collected Fictions , publisher=. 1998 , pages=

    1998

  3. [4]

    2023 , eprint=

    Consciousness in artificial intelligence: insights from the science of consciousness , author=. 2023 , eprint=

    2023

  4. [6]

    Journal of Consciousness Studies , volume=

    Facing up to the problem of consciousness , author=. Journal of Consciousness Studies , volume=. 1995 , publisher=

    1995

  5. [7]

    1996 , publisher=

    The Conscious Mind: In Search of a Fundamental Theory , author=. 1996 , publisher=

    1996

  6. [8]

    Synthese , volume=

    Does a rock implement every finite-state automaton? , author=. Synthese , volume=. 1996 , publisher=

    1996

  7. [9]

    2023 , howpublished=

    Could a large language model be conscious? , author=. 2023 , howpublished=

    2023

  8. [10]

    2026 , howpublished=

    The Vector Grounding Problem , author=. 2026 , howpublished=. doi:10.33735/phimisci.2026.12307 , url=

    work page doi:10.33735/phimisci.2026.12307 2026

  9. [11]

    Nature Reviews Neuroscience , volume=

    The free-energy principle: a unified brain theory? , author=. Nature Reviews Neuroscience , volume=. 2010 , publisher=

    2010

  10. [12]

    Entropy , volume=

    When the map is better than the territory , author=. Entropy , volume=. 2017 , publisher=

    2017

  11. [13]

    Proceedings of the National Academy of Sciences , volume=

    Neural networks and physical systems with emergent collective computational abilities , author=. Proceedings of the National Academy of Sciences , volume=. 1982 , doi=

    1982

  12. [14]

    The forward-forward algorithm: Some preliminary investigations.arXiv preprint arXiv:2212.13345, 2(3):5, 2022

    The Forward-Forward Algorithm: Some Preliminary Investigations , author=. 2022 , eprint=. doi:10.48550/arXiv.2212.13345 , url=

    work page doi:10.48550/arxiv.2212.13345 2022

  13. [15]

    Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences , volume=

    When does a physical system compute? , author=. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences , volume=. 2014 , publisher=

    2014

  14. [16]

    Neuroscience of Consciousness , volume=

    Toward a universal theory of consciousness , author=. Neuroscience of Consciousness , volume=. 2024 , publisher=

    2024

  15. [17]

    Canonical Functionalism: Defining Functional Structure without Observer-Relative Semantic Maps

    Kanai, Ryota and Ma, Shuqin , title=. 2026 , eprint=. doi:10.48550/arXiv.2605.21506 , url=

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2605.21506 2026

  16. [19]

    Neuroscience of Consciousness , volume=

    The case for neurons: a no-go theorem for consciousness on a chip , author=. Neuroscience of Consciousness , volume=. 2024 , publisher=

    2024

  17. [20]

    Neuroscience and Biobehavioral Reviews , volume=

    A beautiful loop: An active inference theory of consciousness , author=. Neuroscience and Biobehavioral Reviews , volume=. 2025 , publisher=

    2025

  18. [21]

    The Abstraction Fallacy: Why

    Lerchner, Alexander , year=. The Abstraction Fallacy: Why

  19. [22]

    Pacific Philosophical Quarterly , volume=

    Materialism and qualia: The explanatory gap , author=. Pacific Philosophical Quarterly , volume=. 1983 , doi=

    1983

  20. [23]

    Cognitive Science , volume=

    Unification by fiat: Arrested development of predictive processing , author=. Cognitive Science , volume=. 2020 , publisher=

    2020

  21. [24]

    Long, Robert and Sebo, Jeff and Butlin, Patrick and Finlinson, Kathleen and Fish, Kyle and Harding, Jacqueline and Pfau, Jacob and Sims, Toni and Birch, Jonathan and Chalmers, David , year=. Taking. doi:10.48550/arXiv.2411.00986 , url=. 2411.00986 , archivePrefix=

    work page doi:10.48550/arxiv.2411.00986

  22. [25]

    2015 , publisher=

    Physical Computation: A Mechanistic Account , author=. 2015 , publisher=

    2015

  23. [26]

    Art, Mind, and Religion , editor=

    Psychological predicates , author=. Art, Mind, and Religion , editor=. 1967 , publisher=

    1967

  24. [27]

    1988 , publisher=

    Representation and Reality , author=. 1988 , publisher=

    1988

  25. [28]

    Behavioral and Brain Sciences , volume=

    Minds, brains, and programs , author=. Behavioral and Brain Sciences , volume=. 1980 , publisher=

    1980

  26. [29]

    1992 , publisher=

    The Rediscovery of the Mind , author=. 1992 , publisher=

    1992

  27. [30]

    Behavioral and Brain Sciences , pages=

    Conscious artificial intelligence and biological naturalism , author=. Behavioral and Brain Sciences , pages=. 2025 , publisher=

    2025

  28. [31]

    Studies in History and Philosophy of Science Part A , volume=

    Computation, individuation, and the received view on representation , author=. Studies in History and Philosophy of Science Part A , volume=. 2010 , publisher=

    2010

  29. [32]

    Triviality arguments about computational implementation , author=. The. 2018 , publisher=

    2018

  30. [33]

    2007 , publisher=

    Mind in Life: Biology, Phenomenology, and the Sciences of Mind , author=. 2007 , publisher=

    2007

  31. [34]

    PLoS Computational Biology , volume=

    Learning action-oriented models through active inference , author=. PLoS Computational Biology , volume=. 2020 , publisher=

    2020

  32. [35]

    2003 , publisher=

    Making Things Happen: A Theory of Causal Explanation , author=. 2003 , publisher=

    2003

  33. [36]

    Neuroscience of Consciousness , volume=

    Computers, meaning, and consciousness , author=. Neuroscience of Consciousness , volume=. 2025 , publisher=

    2025

  34. [37]

    , Barbosa, L

    albantakis2023integrated APACrefauthors Albantakis, L. , Barbosa, L. , Findlay, G. , Grasso, M. , Haun, A.M. , Marshall, W. Tononi, G. APACrefauthors \ 2023 . Integrated information theory ( IIT ) 4.0: Formulating the properties of phenomenal existence in physical terms Integrated information theory ( IIT ) 4.0: Formulating the properties of phenomenal ex...

    work page doi:10.1371/journal.pcbi.1011465 2023

  35. [38]

    APACrefauthors \ 2026

    block2026can APACrefauthors Block, N. APACrefauthors \ 2026 . Can only meat machines be conscious? Can only meat machines be conscious? Trends in Cognitive Sciences 30 4 298--308, APACrefDOI doi:10.1016/j.tics.2025.08.009 APACrefDOI

    work page doi:10.1016/j.tics.2025.08.009 2026

  36. [39]

    APACrefauthors \ 1998

    borges1998exactitude APACrefauthors Borges, J.L. APACrefauthors \ 1998 . On exactitude in science On exactitude in science . Collected Fictions Collected fictions \ ( 325). Penguin . Translated by Andrew Hurley; original work published 1946

    1998

  37. [40]

    Trends in Cognitive Sciences , author =

    butlin2025identifying APACrefauthors Butlin, P. , Long, R. , Bayne, T. , Bengio, Y. , Birch, J. , Chalmers, D. VanRullen, R. APACrefauthors \ 2025 . Identifying indicators of consciousness in AI systems. Identifying indicators of consciousness in AI systems. Trends in Cognitive Sciences (advance online publication) . APACrefURL https://doi.org/10.1016/j.t...

    work page doi:10.1016/j.tics.2025.10.011 2025

  38. [41]

    , Long, R

    butlin2023consciousness APACrefauthors Butlin, P. , Long, R. , Elmoznino, E. , Bengio, Y. , Birch, J. , Constant, A. VanRullen, R. APACrefauthors \ 2023 . Consciousness in artificial intelligence: insights from the science of consciousness. Consciousness in artificial intelligence: insights from the science of consciousness. APACrefURL https://arxiv.org/a...

    Pith/arXiv arXiv 2023

  39. [42]

    APACrefauthors \ 1995

    chalmers1995facing APACrefauthors Chalmers, D.J. APACrefauthors \ 1995 . Facing up to the problem of consciousness Facing up to the problem of consciousness . Journal of Consciousness Studies 2 3 200--219, APACrefURL https://consc.net/papers/facing.pdf APACrefURL

    1995

  40. [43]

    APACrefauthors \ 1996 1

    chalmers1996aconscious APACrefauthors Chalmers, D.J. APACrefauthors \ 1996 1 . The Conscious Mind: In Search of a Fundamental Theory The conscious mind: In search of a fundamental theory . Oxford University Press

    1996

  41. [44]

    APACrefauthors \ 1996 2

    chalmers1996brock APACrefauthors Chalmers, D.J. APACrefauthors \ 1996 2 . Does a rock implement every finite-state automaton? Does a rock implement every finite-state automaton? Synthese 108 3 309--333, APACrefDOI doi:10.1007/BF00413692 APACrefDOI

    work page doi:10.1007/bf00413692 1996

  42. [45]

    APACrefauthors \ 2023

    chalmers2023could APACrefauthors Chalmers, D.J. APACrefauthors \ 2023 . Could a large language model be conscious? Could a large language model be conscious? Boston Review, 9 August 2023 . APACrefURL https://www.bostonreview.net/articles/could-a-large-language-model-be-conscious/ APACrefURL Also available as arXiv:2303.07103

    arXiv 2023

  43. [46]

    \ Milli \`e re, R

    coelhomollomilliere2026 APACrefauthors Coelho Mollo, D. \ Milli \`e re, R. APACrefauthors \ 2026 . The Vector Grounding Problem. The vector grounding problem. Philosophy and the Mind Sciences, 7(1) . APACrefURL https://philosophymindscience.org/index.php/phimisci/article/view/12307 APACrefURL

    2026

  44. [47]

    The free-energy principle: a unified brain theory?Nature Reviews Neuroscience, 11(2): 127–138, February 2010

    friston2010free APACrefauthors Friston, K. APACrefauthors \ 2010 . The free-energy principle: a unified brain theory? The free-energy principle: a unified brain theory? Nature Reviews Neuroscience 11 2 127--138, APACrefDOI doi:10.1038/nrn2787 APACrefDOI

    work page doi:10.1038/nrn2787 2010

  45. [48]

    APACrefauthors \ 2022

    hinton2022forward APACrefauthors Hinton, G. APACrefauthors \ 2022 . The Forward-Forward Algorithm: Some Preliminary Investigations. The forward-forward algorithm: Some preliminary investigations. APACrefURL https://arxiv.org/abs/2212.13345 APACrefURL arXiv:2212.13345

    arXiv 2022

  46. [49]

    APACrefauthors \ 2017

    hoel2017map APACrefauthors Hoel, E.P. APACrefauthors \ 2017 . When the map is better than the territory When the map is better than the territory . Entropy 19 5 188, APACrefDOI doi:10.3390/e19050188 APACrefDOI

    work page doi:10.3390/e19050188 2017

  47. [50]

    Neural Networks and Physical Systems with Emergent Collective Com- putational Abilities

    hopfield1982neural APACrefauthors Hopfield, J.J. APACrefauthors \ 1982 . Neural networks and physical systems with emergent collective computational abilities Neural networks and physical systems with emergent collective computational abilities . Proceedings of the National Academy of Sciences 79 8 2554--2558, APACrefDOI doi:10.1073/pnas.79.8.2554 APACrefDOI

    work page doi:10.1073/pnas.79.8.2554 1982

  48. [51]

    , Stepney, S

    horsman2014does APACrefauthors Horsman, C. , Stepney, S. , Wagner, R.C. & Kendon, V. APACrefauthors \ 2014 . When does a physical system compute? When does a physical system compute? Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences 470 2169 20140182, APACrefDOI doi:10.1098/rspa.2014.0182 APACrefDOI

    work page doi:10.1098/rspa.2014.0182 2014

  49. [52]

    \ Fujisawa, I

    kanai2024toward APACrefauthors Kanai, R. \ Fujisawa, I. APACrefauthors \ 2024 . Toward a universal theory of consciousness Toward a universal theory of consciousness . Neuroscience of Consciousness 2024 1 niae022, APACrefDOI doi:10.1093/nc/niae022 APACrefDOI

    work page doi:10.1093/nc/niae022 2024

  50. [53]

    kanaima2026canonical APACrefauthors Kanai, R. \ Ma, S. APACrefauthors \ 2026 . Canonical Functionalism: Defining Functional Structure without Observer-Relative Semantic Maps. Canonical functionalism: Defining functional structure without observer-relative semantic maps. APACrefURL https://arxiv.org/abs/2605.21506 APACrefURL arXiv:2605.21506

    Pith/arXiv arXiv 2026

  51. [54]

    , Sun, Y

    kanai2025stream APACrefauthors Kanai, R. , Sun, Y. & Baltieri, M. APACrefauthors \ 2025 . The Stream of Computation: Temporal Continuity as a Missing Ingredient for Artificial Consciousness. The stream of computation: Temporal continuity as a missing ingredient for artificial consciousness. PsyArXiv . APACrefURL https://doi.org/10.31234/osf.io/c6jnd APACr...

    work page doi:10.31234/osf.io/c6jnd 2025

  52. [55]

    \ Ludwig, T

    kleiner2024case APACrefauthors Kleiner, J. \ Ludwig, T. APACrefauthors \ 2024 . The case for neurons: a no-go theorem for consciousness on a chip The case for neurons: a no-go theorem for consciousness on a chip . Neuroscience of Consciousness 2024 1 niae037, APACrefDOI doi:10.1093/nc/niae037 APACrefDOI

    work page doi:10.1093/nc/niae037 2024

  53. [56]

    , Friston, K.J

    laukkonen2025beautiful APACrefauthors Laukkonen, R.E. , Friston, K.J. & Chandaria, S. APACrefauthors \ 2025 . A beautiful loop: An active inference theory of consciousness A beautiful loop: An active inference theory of consciousness . Neuroscience and Biobehavioral Reviews 176 106296, APACrefDOI doi:10.1016/j.neubiorev.2025.106296 APACrefDOI

    work page doi:10.1016/j.neubiorev.2025.106296 2025

  54. [57]

    APACrefauthors \ 2026

    lerchner2026abstraction APACrefauthors Lerchner, A. APACrefauthors \ 2026 . The Abstraction Fallacy: Why AI Can Simulate But Not Instantiate Consciousness. The abstraction fallacy: Why AI can simulate but not instantiate consciousness. APACrefURL https://philarchive.org/rec/LERTAF APACrefURL Preprint, PhilArchive, 19 March 2026

    2026

  55. [58]

    APACrefauthors \ 1983

    levine1983materialism APACrefauthors Levine, J. APACrefauthors \ 1983 . Materialism and qualia: The explanatory gap Materialism and qualia: The explanatory gap . Pacific Philosophical Quarterly 64 4 354--361, APACrefDOI doi:10.1111/j.1468-0114.1983.tb00207.x APACrefDOI

    work page doi:10.1111/j.1468-0114.1983.tb00207.x 1983

  56. [59]

    \ Mi kowski, M

    litwin2020unification APACrefauthors Litwin, P. \ Mi kowski, M. APACrefauthors \ 2020 . Unification by fiat: Arrested development of predictive processing Unification by fiat: Arrested development of predictive processing . Cognitive Science 44 7 e12867, APACrefDOI doi:10.1111/cogs.12867 APACrefDOI

    work page doi:10.1111/cogs.12867 2020

  57. [60]

    , Sebo, J

    long2024taking APACrefauthors Long, R. , Sebo, J. , Butlin, P. , Finlinson, K. , Fish, K. , Harding, J. Chalmers, D. APACrefauthors \ 2024 . Taking AI welfare seriously. Taking AI welfare seriously. APACrefURL https://arxiv.org/abs/2411.00986 APACrefURL arXiv preprint, arXiv:2411.00986

    arXiv 2024

  58. [61]

    APACrefauthors \ 2015

    piccinini2015physical APACrefauthors Piccinini, G. APACrefauthors \ 2015 . Physical Computation: A Mechanistic Account Physical computation: A mechanistic account . Oxford University Press

    2015

  59. [62]

    APACrefauthors \ 1967

    putnam1967psychological APACrefauthors Putnam, H. APACrefauthors \ 1967 . Psychological predicates Psychological predicates . W.H. Capitan\ D.D. Merrill\ ( ), Art, Mind, and Religion Art, mind, and religion \ ( \ 37--48). University of Pittsburgh Press

    1967

  60. [63]

    APACrefauthors \ 1988

    putnam1988representation APACrefauthors Putnam, H. APACrefauthors \ 1988 . Representation and Reality Representation and reality . MIT Press

    1988

  61. [64]

    APACrefauthors \ 1980

    searle1980minds APACrefauthors Searle, J.R. APACrefauthors \ 1980 . Minds, brains, and programs Minds, brains, and programs . Behavioral and Brain Sciences 3 3 417--457, APACrefDOI doi:10.1017/S0140525X00005756 APACrefDOI

    work page doi:10.1017/s0140525x00005756 1980

  62. [65]

    APACrefauthors \ 1992

    searle1992rediscovery APACrefauthors Searle, J.R. APACrefauthors \ 1992 . The Rediscovery of the Mind The rediscovery of the mind . MIT Press

    1992

  63. [66]

    APACrefauthors \ 2025

    seth2025conscious APACrefauthors Seth, A.K. APACrefauthors \ 2025 . Conscious artificial intelligence and biological naturalism Conscious artificial intelligence and biological naturalism . Behavioral and Brain Sciences 1--42, APACrefDOI doi:10.1017/S0140525X25000032 APACrefDOI

    work page doi:10.1017/s0140525x25000032 2025

  64. [67]

    APACrefauthors \ 2010

    sprevak2010computation APACrefauthors Sprevak, M. APACrefauthors \ 2010 . Computation, individuation, and the received view on representation Computation, individuation, and the received view on representation . Studies in History and Philosophy of Science Part A 41 3 260--270, APACrefDOI doi:10.1016/j.shpsa.2010.07.008 APACrefDOI

    work page doi:10.1016/j.shpsa.2010.07.008 2010

  65. [68]

    APACrefauthors \ 2018

    sprevak2018triviality APACrefauthors Sprevak, M. APACrefauthors \ 2018 . Triviality arguments about computational implementation Triviality arguments about computational implementation . M. Sprevak\ M. Colombo\ ( ), The Routledge Handbook of the Computational Mind The Routledge handbook of the computational mind \ ( \ 175--191). Routledge

    2018

  66. [69]

    APACrefauthors \ 2007

    thompson2007mind APACrefauthors Thompson, E. APACrefauthors \ 2007 . Mind in Life: Biology, Phenomenology, and the Sciences of Mind Mind in life: Biology, phenomenology, and the sciences of mind . Harvard University Press

    2007

  67. [70]

    , Seth, A.K

    tschantz2020learning APACrefauthors Tschantz, A. , Seth, A.K. & Buckley, C.L. APACrefauthors \ 2020 . Learning action-oriented models through active inference Learning action-oriented models through active inference . PLoS Computational Biology 16 4 e1007805, APACrefDOI doi:10.1371/journal.pcbi.1007805 APACrefDOI

    work page doi:10.1371/journal.pcbi.1007805 2020

  68. [71]

    APACrefauthors \ 2003

    woodward2003making APACrefauthors Woodward, J. APACrefauthors \ 2003 . Making Things Happen: A Theory of Causal Explanation Making things happen: A theory of causal explanation . Oxford University Press

    2003

  69. [72]

    APACrefauthors \ 2025

    worden2025computers APACrefauthors Worden, R. APACrefauthors \ 2025 . Computers, meaning, and consciousness Computers, meaning, and consciousness . Neuroscience of Consciousness 2025 1 niaf057, APACrefDOI doi:10.1093/nc/niaf057 APACrefDOI

    work page doi:10.1093/nc/niaf057 2025