Normalized area under S (AUSN)

Average of per-layer S(ℓ) scores, summarizing the breadth of anchoring trajectory.

Neighborhood — ranked by edge-count

concept

normalized area under S-curve AUSN
related_to
Average S(ℓ) across layers; another geometry summary.
normalized area AUSN
related_to
Average of S(ℓ) across layers.
Layer-wise anchoring trajectory
associated_with
Plot of per-layer anchoring score S(ℓ) across model depth, revealing early dip, mid-layer peak, late standardization.

artifact

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.

Normalized Area Under Anchoring Trajectory (AUS_N)concept0.830
Mean of S(ℓ) across layers; weaker geometry correlate with θ50
AUSN mean -2.119 ± 0.198finding0.784
Normalized area under S(ℓ) averaged over seeds.
Geometry summaries (Sbmax, AUSN)method0.761
Peak anchoring (Sbmax) and normalized area under the S(ℓ) curve (AUSN) used to summarize trajectory.
AUS_N is a weaker correlate of θ50 than S_max across E3 backbonesfinding0.758
E3 finding distinguishing the two geometry summaries; breadth less predictive than peak height
Peak anchoring Sbmax and normalized area AUSN correlate with per-item success and internal shot midpoints θ50, providing a geometry-to-behavior bridge.claim0.754
Main interpretation of E3.
Layer-wise geometry summaries (Sbmax, AUSN) predict internal few-shot thresholds θ50claim0.731
Claim that geometry-to-behavior correlates exist
Layer Normalization (Ba et al., 2016b)concept0.714
Layer normalisation used in transformer and in TEM-t position encoding preprocessing.
Hypothesis: Peak alignment location S_max and normalized trajectory area AUS_N predict shot midpoints θ50hypothesis0.708
E3 prediction that internal geometry provides a bridge to behavioral thresholds