claim

active

claim:a-system-s-state-and-structure-encode-an-implicit-and-probabilistic-model-of-the-environment

A system's state and structure encode an implicit and probabilistic model of the environment.

Foundational claim about internal representation emerging from free energy optimization.

Source paper

extracted_from

A Free energy principle for the brain (lecture summary)

(2008) · Karl Friston

Neighborhood — ranked by edge-count

Communities (2)

community

Mechanistic interpretability & model evaluation
members_of
Spans attention head decomposition, benchmark awareness, and genomic pathogenicity prediction via neural models.
Latent capacity, representation, and internal models
members_of
Studies of how neural systems (biological and AI) encode implicit environmental models and adaptive capacities that may be gated or hidden from observable behavior.

Frameworks (1)

framework

Free Energy Principle
supports
A 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.

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Any system that persists must minimise surprisal, thereby gathering evidence for its own generative model.quote0.764
Opening sentence defining self-evidencing.
what is the precise characterization of the perceptual representational format in which information exists as a specific, sustained, globally constitutive structure?question0.761
Open theoretical problem CIMC acknowledges: precisely characterizing the representational format of perception
Generative models are entailed by adaptive behavior, not explicitly encoded in brain statesclaim0.760
Distinction from Bayesian brain: generative model is consequence of dynamics, not neural representation
When a system of living processes acts in a human environment, two kinds of structures will appear within reach of every person: a unique private world and an attached public world.hypothesis0.760
Predictive claim about the automatic spatial output of living process
If internal states encode a probability density over external states, then it should be possible to predict external states from internal states.hypothesis0.754
The testable hypothesis driving the active inference analysis in the simulation.
Any system that persists must minimise surprisal, thereby gathering evidence for its own generative model, a process known as self-evidencing.claim0.752
Foundational claim of the paper, defining self-evidencing.
Language models contain interpretable computational structure encoded in their parameter weights, not irreducibly impenetrable complexityhypothesis0.750
Core empirical hypothesis of the paper, supported by successful VPD decomposition yielding ~10,000 interpretable subcomponents across 24 weight matrices.
The physical structure of the world is generated by its processes.claim0.750
States that the form of buildings and cities is an outcome of the processes that create them, even when unintended.