Complexity proxies have nontrivial but inconsistent generalization correlations under best-layer selection. The reported average correlations range from 0.35 to 0.56, while a random baseline also reaches 0.4 under the same selection strategy. Dataset-specific performance varies widely, including weak associations on emotion and Yahoo topic pairs and strong positive or negative associations on some other tasks.

Complexity proxies have nontrivial but inconsistent generalization correlations under best-layer selection. The reported average correlations range from 0.35 to 0.56, while a random baseline also reaches 0.4 under the same selection strategy. Dataset-specific performance varies widely, including weak associations on emotion and Yahoo topic pairs and strong positive or negative associations on some other tasks. · CiteArk

Measurement results

0/199 assessed

0 supported0 disputed or conflicting199 not assessed

The complete result group stays with its claim. Assessed rows come first; their judgments do not replace the whole-claim conclusion. Expand a row for conditions, sources, and evidence history.

Each row is a measurement with its reported value, latest available observation, and cumulative evidence state.
Metric and conditions	Reported	Latest observation	Evidence judgment
	0.35 dimensionless	—	Not assessed
	0.56 dimensionless	—	Not assessed
	0.4 dimensionless	—	Not assessed
layer: 39 · dataset: successive-arithmetic-plus1 · complexityMetric: RankMe (activation) · selectedExtremum: rho-plus	0.62 dimensionless	—	Not assessed
layer: 14 · dataset: successive-arithmetic-plus1 · complexityMetric: RankMe (activation) · selectedExtremum: rho-minus	-0.46 dimensionless	—	Not assessed
layer: 11 · dataset: successive-letters · complexityMetric: RankMe (activation) · selectedExtremum: rho-plus	0.28 dimensionless	—	Not assessed
layer: 25 · dataset: successive-letters · complexityMetric: RankMe (activation) · selectedExtremum: rho-minus	-0.3 dimensionless	—	Not assessed
layer: 40 · dataset: successive-even-plus2 · complexityMetric: RankMe (activation) · selectedExtremum: rho-plus	0.65 dimensionless	—	Not assessed
layer: 22 · dataset: successive-even-plus2 · complexityMetric: RankMe (activation) · selectedExtremum: rho-minus	-0.67 dimensionless	—	Not assessed
layer: 5 · dataset: successive-number-words · complexityMetric: RankMe (activation) · selectedExtremum: rho-plus	0.29 dimensionless	—	Not assessed
layer: 16 · dataset: successive-number-words · complexityMetric: RankMe (activation) · selectedExtremum: rho-minus	-0.52 dimensionless	—	Not assessed
layer: 3 · dataset: repetitive-letter-counting · complexityMetric: RankMe (activation) · selectedExtremum: rho-plus	0.23 dimensionless	—	Not assessed

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results