method
active
method:pseudo-likelihood-maximization-with-ebic-isingfitPseudo-likelihood maximization with EBIC (IsingFit)
Procedure for fitting Ising couplings.
Neighborhood — ranked by edge-count
Papers (1)
paper
- Do Sparse Autoencoders Capture Concept Manifolds?citesmentions
Methods (1)
method
- Fits Ising over binarized codes, Louvain clustering, PCA spectral-gap validation.
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.
- Claim about computational feasibility of pseudo-intents.
- Retrodiction of known phenomenon.
- Equivalence of optimal predictor to the physics of the data.
- Proposed conjecture in §4.3.1.
- Headline result (Figure 1).
- Variant classifier capturing alignment faking motivated by general self-preservation rather than specific preference conflict
- Describes the epistemic function of variational free energy.
- Methods for bottom-up model space construction; contrasted with top-down BMR approach of this paper