The kernel-activation ablation finds no consistent improvement from the listed kernel approximations over simple pointwise activations. Random Feature Attention is the lowest-perplexity entry in the table, while Positive Random Features (Performer) is the highest; the paper retains Swish as the default and notes that removing the activation may be simpler but was not extensively tested.

The kernel-activation ablation finds no consistent improvement from the listed kernel approximations over simple pointwise activations. Random Feature Attention is the lowest-perplexity entry in the table, while Positive Random Features (Performer) is the highest; the paper retains Swish as the default and notes that removing the activation may be simpler but was not extensively tested. · CiteArk

Measurement results

0/8 assessed

0 supported0 disputed or conflicting8 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.
Reported	Latest observation	Evidence judgment
11.58 perplexity	—	Not assessed
11.66 perplexity	—	Not assessed
11.62 perplexity	—	Not assessed
11.73 perplexity	—	Not assessed
11.64 perplexity	—	Not assessed
11.97 perplexity	—	Not assessed
11.57 perplexity	—	Not assessed
12.21 perplexity	—	Not assessed

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results