Self-Evidencing

Concise framing of action-perception cycle whereby agents minimize surprise through perception and action.

Neighborhood — ranked by edge-count

paper

thinker

framework

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

claim

concept

Self-Evidencing Brain
related_to
Hohwy's (2016) characterization: brain acts to maximize its own model evidence; consistent with active inference summary
self-evidencing continues unimpeded after transition
extends
After the prior removal, the agent still minimizes surprisal but without attributing outcomes to a bounded self; grounded in structural realism.
Niche / Phenotype Maintenance
associated_with
In active inference, the ultimate goal is to maintain a consistent set of behaviors (a niche) that preserves the agent's phenotypic identity.

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.

One dimension of self-evidencing is provably impossible: evidencing the boundary that would constitute the agent as an entity separate from their environment.claim0.823
Central thesis of the paper.
Selfingconcept0.813
Process of reifying one's identity as an independent self; meditation practices aim to decrease selfing.
Any system that persists must minimise surprisal, thereby gathering evidence for its own generative model, a process known as self-evidencing.claim0.787
Foundational claim of the paper, defining self-evidencing.
Self-evidencing is not only unimpaired but improved after emptiness realisation, as the pruned model is more parsimonious without loss of accuracyclaim0.787
Addresses the concern that emptiness realisation might undermine adaptive functioning
embodied recognition of the evidencing impossibilityconcept0.776
The process by which an agent realizes through practice that the self-environment boundary is unevidenceable, leading to awakening.
Self-reflectionconcept0.774
The ability of reasoning LLMs to review and revise previous reasoning steps during inference
Selfing Processconcept0.773
self-observationconcept0.769
The ability of a model to observe its own state, measured by Koan Battery; can be lifted by contemplative prompts.