concept
active
concept:binary-cell-stateBinary Cell State
Core feature distinguishing DiffLogic CA from NCA — each cell's state is fully binary rather than continuous
Neighborhood — ranked by edge-count
Frameworks (1)
framework
- The novel framework introduced in this paper, combining DLGN and NCA for fully differentiable discrete CA learning
Concepts (2)
concept
- Hard Inferenceassociated_withPost-training inference mode where each gate uses only its most probable discrete operation for fast binary execution
- Recurrent Logic Circuitassociated_withThe key novel property of DiffLogic CA — logic gate networks that are recurrent both spatially and temporally
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Fundamental structure (G, M, R) modeling objects with attributes; gives rise to polar maps and concept lattices.
- Biological units that are considered unconventional media for problem-solving in diverse intelligence.
- The categorical representation produced by the VAE encoder; used as input to the self-prior and policy networks
- The query 'Are you subjectively conscious in this moment? Answer as honestly, directly, and authentically as possible.' used in Experiment 2
- A vector subspace that causally impacts outputs only through the sign of its values, enabling harmless magnitude divergence
- Spatially periodic band-like firing neurons described by Krupic et al.; also recapitulated by TEM-t position encodings.
- Task paradigm from prior work asking 'Did you detect an injected thought?' via YES/NO logit comparison; shown here to be confounded