normalized area under S-curve AUSN

Average S(ℓ) across layers; another geometry summary.

Neighborhood — ranked by edge-count

method

layer-wise trajectory analysis
associated_with
Computing per-layer S(ℓ) to summarize geometry.

concept

normalized area AUSN
related_tosame_as
Average of S(ℓ) across layers.
Normalized area under S (AUSN)
related_to
Average of per-layer S(ℓ) scores, summarizing the breadth of anchoring trajectory.
internal threshold θ50
associated_with
Few-shot midpoint in E3's geometric analysis.

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)concept0.808
Mean of S(ℓ) across layers; weaker geometry correlate with θ50
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 backbonesfinding0.755
E3 finding distinguishing the two geometry summaries; breadth less predictive than peak height
AUSN mean -2.119 ± 0.198finding0.742
Normalized area under S(ℓ) averaged over seeds.
Layer-wise geometry summaries (Sbmax, AUSN) predict internal few-shot thresholds θ50claim0.729
Claim that geometry-to-behavior correlates exist
Peak anchoring Sbmax and normalized area AUSN correlate with per-item success and internal shot midpoints θ50, providing a geometry-to-behavior bridge.claim0.729
Main interpretation of E3.
Hypothesis: Peak alignment location S_max and normalized trajectory area AUS_N predict shot midpoints θ50hypothesis0.711
E3 prediction that internal geometry provides a bridge to behavioral thresholds
Layer Normalization (Ba et al., 2016b)concept0.706
Layer normalisation used in transformer and in TEM-t position encoding preprocessing.