method
active
method:whitening-and-z-scoring-procedure

whitening and z-scoring procedure

Calibration protocol: whiten embeddings on dev pool, z-score ρd and dr per layer.

Neighborhood — ranked by edge-count

Concepts (1)

concept
  • Composite score S = ρd − dr − log k predicting anchoring success.

Methods (3)

method

Artifacts (1)

artifact

Conceptual bridges

2-hop · via this method's ideas

Where ideas in this method connect to the rest of the corpus — the same concept, an analogy, or a restatement elsewhere.

Related by similarity (8)

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.

  • Preprocessing step using dev-set covariance to standardize span embeddings before computing S
  • Per-(emotion, token) z-score computed as injected emotion activation minus mean of 170 other probes, contrasted against no-steering baseline
  • Alternative interpretation of IID mass-mean probing as projection onto θ_mm after Mahalanobis whitening
  • Standardization of ρd and dr components using development-set mean and standard deviation.
  • Adaptive gradient clipping method used during training to mitigate spikes
  • Preprocessing step that uses dev-set covariance to standardize embedding scales before computing ρd and dr.
  • A method of reversing the figure-ground of a plan to test whether the space reads as a solid, connected figure, revealing its positive character.
  • Method of cultivating introspective behavior by mirroring back a model's self-discoveries, creating feedback loops via ICL.