Perception Stage

First stage of DiffLogic CA update where each cell gathers information from neighboring cells via logic gate kernels

Neighborhood — ranked by edge-count

framework

Differentiable Logic Cellular Automata (DiffLogic CA)
implements
The novel framework introduced in this paper, combining DLGN and NCA for fully differentiable discrete CA learning

concept

Sobel Filters
cites
Used in traditional NCA for spatial gradient perception; replaced by logic gate kernels in DiffLogic CA

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.

Perceptionconcept0.835
Equated with inference of past, present and future hidden states via minimization of variational free energy.
Perception-Action Cycleconcept0.817
Circular causality between perception and action; central to enactive interpretation
Introspection Stagemethod0.793
Stage 3 of character training: SFT on synthetic introspective data generated by post-distillation checkpoint
Perception And Cognitionconcept0.787
Distillation Stagemethod0.769
Stage 2 of character training: DPO from teacher model to student model to transfer desired behavioral expressions
Update Stageconcept0.760
Second stage of DiffLogic CA where a DLGN computes each cell's new binary state from perception output and current state
field-like perceptionconcept0.758
Perception that is smooth and can be evaluated at any point, like a differentiable field; Antra's functionalist interpretation.
Stages of Inferenceframework0.757
The perspective that LLM inference decomposes into distinct computational stages, which the paper extends to looped models