Generative Model

Agent's internal probabilistic model of environment; enables belief inference about hidden states given outcomes.

Neighborhood — ranked by edge-count

paper

framework

Active Inference
associated_withimplements
Foundational framework by Karl Friston; the paper extends it to three hierarchical levels for modeling meta-awareness.

claim

Generative models are not structural representations; recognition densities are
about
Direct refutation of structural representationalist interpretation; recognition density encodes information, not generative model
Generative models function as control systems that guide adaptive action policy selection
about
Core claim: generative models regulate organism behavior to maintain phenotypic bounds, not represent external world
Generative models are entailed by adaptive behavior, not explicitly encoded in brain states
about
Distinction from Bayesian brain: generative model is consequence of dynamics, not neural representation

concept

Perception
associated_withimplements
Equated with inference of past, present and future hidden states via minimization of variational free energy.
Mixed Generative Models
related_to
Generative models combining discrete and continuous states to link decisions and movements.
free energy
associated_with
Thermodynamic potential ΔF = ΔE − TΔS; domain walls form if ΔF < 0
Learning
associated_with
Inference of parameters encoding contingencies of the world (e.g., likelihood matrix A) at slower timescale than perception.
Markov Blanket
associated_with
A statistical partition of states that separates internal states from external hidden states; fundamental to self-organization in the paper.
Structure Learning
implements
Updating the structure of the generative model to better account for observations via Bayesian model reduction and expansion.
Likelihood Array (A matrix)
associated_with
High-dimensional array mapping hidden states to outcomes; key learned quantity in the paradigm
Perception-Action Cycle
associated_with
Circular causality between perception and action; central to enactive interpretation
Adaptive Behavior
associated_with
Organism's belief-guided action selection that instantiates generative model and maintains phenotypic states
Transition Matrix (B matrix)
associated_with
Prescribes transitions among hidden state factors under action; encodes policy-dependent dynamics

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.

Hyper Generative-Modelconcept0.840
Globally-acting model that recursively monitors and updates how all inference layers interact; substrate of epistemic depth
modelconcept0.819
A representation that captures relevant aspects of a system; according to the theorem, the regulator must embody this.
Generative Programconcept0.816
A set of instructions for making something (contrasted with a descriptive blueprint), as in embryonic development.
Generative Model Fitting to AI Behaviormethod0.805
Proposed future method: fit active inference generative models to AI behavior to verify wise world model internalization
generative processconcept0.796
A process where the whole creates the conditions for the part, following a vital rhythm in which large precedes small.
Language Modelsconcept0.789
Primary substrate for manifold steering experiments; demonstrates method on reasoning and in-context tasks.
Reasoning Modelsconcept0.786
Class of large language models designed to produce extended chain-of-thought before answering, studied in this paper
What is the generative model that best explains observable data from a behaving agent?question0.782
Central challenge for active inference stated in Discussion.