method
active
method:per-dev-z-scalingper-dev z-scaling
Standardizing ρd and dr using dev-set means and stds to form dimensionless components of S.
Neighborhood — ranked by edge-count
Concepts (1)
concept
- anchoring strength Sassociated_withComposite score S = ρd − dr − log k predicting anchoring success.
Methods (1)
method
- Per-dev z-scoringrelated_toStandardization of ρd and dr components using development-set mean and standard deviation.
Datasets (1)
dataset
- development set (dev pool)associated_withSet of 1,000 prompts with k=3 examples used for whitening and z-scoring calibration.
Artifacts (1)
artifact
- Main paper presenting UCCT and semantic anchoring framework.
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.
- Preprocessing pipeline for standardizing ρd, dr, and S across layers/models using dev-set covariance
- Techniques that leverage AI to help humans more efficiently supervise AI.
- Mechanisms by which smaller competent subunits bind into a higher-level Self with larger goals; key example via gap junction connections.
- Used in the color cooccurrence experiment to embed colors into 3D space preserving dissimilarity matrix distances
- Implementation detail weighting softmax by log(n_memories) to prevent down-weighting of attention values as memory set grows.
- Interpretive process for transforming many-valued contexts into formal contexts via scale attributes.
- Observation that SAE loss decreases as a power law with compute budget.
- The pressure on models trained on more tasks to find representations that generalize across all tasks, reducing the solution space