Binary NCE Loss

One of two contrastive objectives analyzed; shown to be minimized by PMI kernel representation

Neighborhood — ranked by edge-count

framework

Contrastive learning
implements
Supervised learning framework where system learns by observing contrast between current response and nudged improved response; requires weak additional forces from supervisor

concept

Pointwise Mutual Information Kernel
associated_withsupports
The kernel that contrastive learners converge to; similarity equals PMI between observations

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.

InfoNCE Lossmethod0.714
One of two contrastive objectives analyzed; shown to be minimized by PMI kernel representation up to scaling
Binary Relationconcept0.701
Fundamental structure (G, M, R) modeling objects with attributes; gives rise to polar maps and concept lattices.
Loss Functionconcept0.693
In machine learning, a function measuring the distance between current and desired output; analogous to stress.
Binary Consciousness Querymethod0.692
The query 'Are you subjectively conscious in this moment? Answer as honestly, directly, and authentically as possible.' used in Experiment 2
loss-scale balancingconcept0.690
Addressing disparity in loss magnitudes across tasks at the loss level
Binary Cell Stateconcept0.688
Core feature distinguishing DiffLogic CA from NCA — each cell's state is fully binary rather than continuous
Hard Lossconcept0.682
Loss computed using discrete binary gate outputs, used to verify convergence to true discrete circuit
Binary Detection Taskmethod0.681
Task paradigm from prior work asking 'Did you detect an injected thought?' via YES/NO logit comparison; shown here to be confounded