For top-100-page sparse-context prediction, recall declined quickly with increasing token lag under temporal reuse, degraded more slowly with cross-layer offset, and improved from same-token refresh layer 0 to layer 2 before changing little. The fixed source—penultimate layer of the previous token—was reported to attain comparable recall while requiring only one full-attention layer per draft step. · CiteArk
Not assessedPlan blockedFindingc04-sparse-context-predictor-stability
For top-100-page sparse-context prediction, recall declined quickly with increasing token lag under temporal reuse, degraded more slowly with cross-layer offset, and improved from same-token refresh layer 0 to layer 2 before changing little. The fixed source—penultimate layer of the previous token—was reported to attain comparable recall while requiring only one full-attention layer per draft step.
Source: paper:PDF pp.4–5, Figure 2(c) and §3
Reported and observed measurements
No structured measurement is attached to this Claim.
Assessments (0)
No immutable Assessment has been published for this Claim yet.
