Self-Prior

The key novel contribution: an internal model that learns the density of familiar multisensory experiences and drives mark-removal behavior through mismatch with the free energy principle

Neighborhood — ranked by edge-count

Papers (1)

paper

Active Inference with a Self-Prior in the Mirror-Mark Task
introduces

Methods (2)

method

Cross-Modal Sampling
supports
Technique used to demonstrate that the self-prior captures visual–proprioceptive associations by recovering visual appearance from proprioception alone
GPT-like Transformer Autoregressive Model (Self-Prior)
implements
The self-prior is implemented as a GPT-like transformer that autoregressively models the joint distribution of the unified latent state

Concepts (8)

concept

Self-Other Distinction
implements
The implicit capacity the self-prior implements by assigning high density to familiar self-states and low density to non-self states
Probabilistic Body Schema
implements
The paper frames the self-prior as a probabilistic body schema capturing visual–proprioceptive associations
Density Model of Self-Experience
implements
The self-prior functions as a density model over the agent's familiar multisensory states in latent space
Kim et al. 2025: Emergence of goal-directed behaviors via active inference with self-prior (arXiv:2504.11075)
introduces
Predecessor paper introducing the self-prior concept for goal-directed behavior emergence
Predictive Coding Account of Self-Recognition
analogous_to
Apps and Tsakiris's proposal that self-recognition can be modeled probabilistically under the free energy principle
Kinesthetic-Visual Matching
implements
A core requirement of the inductive theory of mirror self-recognition, implemented by the self-prior's visual-proprioceptive associations
Multisensory Integration
implements
The self-prior learns associations between visual and proprioceptive modalities without explicit design
Preferred Distribution
extends
In active inference, the distribution over goal states; here replaced by the learned self-prior rather than a hand-specified prior

Claims (1)

claim

Density evaluation of the self-prior in latent space approximates density evaluation in observation space because the latent state is a sufficient statistic of the observation
supports
Theoretical justification for implementing the self-prior in latent rather than observation space

Frameworks (1)

framework

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

Artifacts (1)

artifact

Self-Prior Mirror Code Repository (github.com/kim135797531/self-prior-mirror)
about
Released simplified robot-based implementation to support reproducibility

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.

Prior Beliefsconcept0.809
Beliefs about states before data; used to transcribe task instructions into agent's generative model
Prior Intentionconcept0.803
Cognitive bifurcation event where second-order contextual constraints reorganize semantic space, establishing weighted alternatives for action.
Self-Referenceconcept0.795
Central phenomenon of the paper: systems that refer to themselves in ways problematic for conventional logic but constitutive of life.
Prior Preferencesconcept0.793
Target distribution over states or outcomes encoded in the generative model; goal states.
Selfingconcept0.792
Process of reifying one's identity as an independent self; meditation practices aim to decrease selfing.
The self-prior operates as an internal criterion for distinguishing self from non-self, without external reward or explicitly computed sticker locationclaim0.787
Central interpretive claim of the paper, supported by EFE decrease after sticker removal
the selfconcept0.780
The interior awareness, consciousness, and felt identity that each person experiences; absent from mechanistic cosmology.
Self-Correctionconcept0.776
Reasoning pattern where model reverses a compliance tendency and returns toward refusal, associated with better safety in QwQ-32B