Hard Inference

Post-training inference mode where each gate uses only its most probable discrete operation for fast binary execution

Neighborhood — ranked by edge-count

concept

Binary Cell State
associated_with
Core feature distinguishing DiffLogic CA from NCA — each cell's state is fully binary rather than continuous
Hard Loss
associated_with
Loss computed using discrete binary gate outputs, used to verify convergence to true discrete circuit

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.

perceptual inferenceconcept0.792
The process of inferring causes of sensory inputs, a key aspect of the free-energy minimization scheme.
Bayesian Inferencemethod0.785
Natural Language Inferenceconcept0.782
Three-way classification task (entailment, contradiction, neutral) leveraged to measure dialogue diversity
Active Inferenceframework0.773
Foundational framework by Karl Friston; the paper extends it to three hierarchical levels for modeling meta-awareness.
Inference to the Best Explanationconcept0.768
Methodological principle applied to favor identity over correlation between signed evaluation and felt valence
Stages of Inferenceframework0.760
The perspective that LLM inference decomposes into distinct computational stages, which the paper extends to looped models
inference of sentienceconcept0.757
Attributing subjective experience based on observable embodied behaviours.
Message Passing Inferenceconcept0.756
Algorithmic framework for probabilistic inference in graphical models.