framework
active
framework:integrated-information-theoryIntegrated Information Theory
Tononi et al. framework quantifying consciousness via integration; provides mathematical tools for measuring agent complexity.
Neighborhood — ranked by edge-count
Papers (1)
paper
Thinkers (4)
thinker
- Giulio Tononiassociated_withintroducesDeveloper of integrated information theory; provides formal tools for measuring integration and consciousness in systems.
- Graham FindlaystudiesCo-author of a recent paper applying IIT to distinguish intelligence from consciousness in LLMs; argues feedforward LLMs yield low Φ.
- Isaac NemirovskystudiesAuthor of a key precedent study implementing IIT on resting-state fMRI data whose methodology this study closely adapts.
- Matjaz GamsstudiesAuthor who assessed ChatGPT consciousness using IIT alongside Turing Test, concluding low integration precludes consciousness.
Concepts (9)
concept
- Cognitive Light Coneassociated_withConcept defining self by the spatiotemporal scale and nature of goals a system can pursue; limits of concern demarcate identity.
- The primary paper being extracted — applies IIT 3.0 and 4.0 to LLM representation sequences derived from ToM test data to investigate whether consciousness phenomena can be observed.
- Consciousnessassociated_withCore concept: capacity to experience as a subject; argued to be substrate-independent and achievable across diverse biological systems.
- Substrate IndependencecontradictsIdea that functions can be achieved without contingency of particular material or physical medium; used to argue sentience need not require neural tissue.
- IndividualityimplementsFormal notion of what constitutes an individual agent; bridges Buddhist and information-theoretic perspectives.
- Synergistic Informationassociated_withInformation-theoretic measure (Edlund et al.) characterizing interdependencies in agent-environment systems.
- Recurrent IntegrationimplementsComputational property emphasized across consciousness theories as necessary for conscious processing
- Foundational axioms of IIT from which postulates about physical systems are derived; applied to the RN in this study.
- Multi Informationassociated_withMultivariate information transmission (McGill 1954); a measure of total dependence among variables.
Claims (3)
claim
- Point of genuine disagreement with IIT and GWT
- Motivates the hybrid approach combining IIT, Span Representation, and multiple criteria.
- CIMC's explicit rejection of IIT as operating outside the representationalist and functionalist framework
Frameworks (7)
framework
- Free Energy Principleassociated_withA foundational variational principle from statistical physics that formalizes how self-organizing systems maintain structural integrity and adapt to their environment by minimizing free energy—a mathematical bound on surprise or prediction error. Originally developed by Karl Friston, the framework unifies action, perception, and learning as processes of active inference, where systems both update internal models of the world and act upon it to reduce the divergence between predictions and observations.
- Formal mathematical framework (Bialek, Tononi, etc.) proposed to characterize autonomous agents and synergies between them.
- Autopoiesisassociated_withMaturana-Varela principle of self-maintaining systems that organize themselves through internal feedback; extended here to biological, technological, and hybrid systems.
- Stress Care Intelligence Loopassociated_with
- Chalmers' problem: why structural/functional criteria should correlate with subjective experience; acknowledged as unsolvable in 3rd person.
- IIT 3.0extendsVersion 3.0 of IIT, used to compute Φmax and Conceptual Information (CI) from LLM representation networks.
- Learning-Feeling IdentityextendsThe paper's own framework identifying signed evaluative computation with phenomenal valence in learning systems
Hypotheses (1)
hypothesis
- The theoretical hypothesis tested across all four experiments; motivated by convergence of GWT, RPT, HOT, IIT, predictive processing on recurrent/self-referential dynamics
Artifacts (1)
artifact
- Key paper finding structured first-person descriptions in LLMs claiming awareness or subjective experience during self-referential processing.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Framework treating phenomena as information flows and exchanges; adopted by Friedman and others to model design as informational process.
- Mathematical theory of communication and information capacity; Sloman argues Schrödinger anticipated its relevance for genetic coding.
- Classical quantitative theory of information; paper seeks to reconcile with qualitative domain-theoretic approaches.
- Information theory offers a language to characterize such entities and synergies between them.claim0.795Claim that information-theoretic measures are suitable to model self and agency.
- Formal framework by Krakauer et al. (2020) for defining an individual based on information theory.
- Chapter 6 explores whether information-theoretic models (Dretske) can ground action causation; concludes they cannot dissolve equivocation problem.
- The field providing the result that no finite system can measure entanglement entropy across its own boundary.
- Integration of signals across components to compute holistic states, a hallmark of organismic individuality and basal cognition