Under the same SPG training budget, the IM reward curve remains above an entropy-scored masking variant throughout training. The paper concludes that marginal token predictability alone does not preserve contextual structure as effectively as the rollout-derived neighbor-confidence-shift score. · CiteArk
Not assessedPlan blockedFindingclaim-011-entropy-reward-comparison
Under the same SPG training budget, the IM reward curve remains above an entropy-scored masking variant throughout training. The paper concludes that marginal token predictability alone does not preserve contextual structure as effectively as the rollout-derived neighbor-confidence-shift score.
Source: paper-fixed:PDF pp. 8–9, Section 4.2 Q5 and Figure 3(b)
Reported and observed measurements
No structured measurement is attached to this Claim.
Assessments (0)
No immutable Assessment has been published for this Claim yet.
