finding

active

finding:passing-a-sticker-bearing-latent-through-the-self-prior-removes-the-sticker-in-reconstruction-confirming-distribution-favors-sticker-free-state

Passing a sticker-bearing latent through the self-prior removes the sticker in reconstruction, confirming distribution favors sticker-free state

Shows the self-prior's generative distribution rejects sticker-bearing states

Source paper

extracted_from

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

(2026) · Dongmin Kim · Hoshinori Kanazawa · Yasuo Kuniyoshi

Neighborhood — ranked by edge-count

Concepts (1)

concept

Density Model of Self-Experience
supports
The self-prior functions as a density model over the agent's familiar multisensory states in latent space

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.

The self-prior operates as an internal criterion for distinguishing self from non-self, without external reward or explicitly computed sticker locationclaim0.808
Central interpretive claim of the paper, supported by EFE decrease after sticker removal
The sticker-removal behavior induced by the self-prior corresponds to stimulus-elicited intention rather than endogenous intention, aligning with the developmental view of early intentional agencyclaim0.800
Connects the model's behavior to Zaadnoordijk and Bayne's taxonomy of intentional agency
Samples drawn from the trained self-prior correspond to sticker-free self in diverse posesfinding0.797
Demonstrates the self-prior learned the sticker-free body distribution as intended
Such priors suppress the inherent contextuality of the boundary.claim0.757
Explains why the boundary appears fixed: the prior hides its context-dependent nature.
Strong priors require higher-cohesion anchors to overcome, manifesting as delayed thresholds or reduced transferhypothesis0.746
Prediction for Experiment 1 cross-domain anchoring
A sensory anomaly (sticker mismatch) can itself become an intrinsic drive for action under active inference, even without external rewardclaim0.745
Core mechanism claim linking mismatch detection to behavior through EFE minimization
Any system that persists must minimise surprisal, thereby gathering evidence for its own generative model, a process known as self-evidencing.claim0.739
Foundational claim of the paper, defining self-evidencing.
The separation prior sigma is a self-reinforcing prior that gains precision simply by being used, decoupled from whether its use remains optimalclaim0.734
Explains developmental entrenchment of the separation prior via habit dynamics in active inference