rollouts can occupy about 70% of elapsed training time in SortedRL's motivating example at a 16K maximum generation length

Name: rollouts can occupy about 70% of elapsed training time in SortedRL's motivating example at a 16K maximum generation length
License: https://aidatacenterguide.com/terms#intellectual-property

~70%observed

Value kind	observed — Reported measurements, counts, and specifications keep the precision and scope stated by their source; an exact specification is not treated as a range.
Scope	phase-duration share in a motivating example; not a measured FLOP, energy or fleet-capacity share
As of	2026-03-24
Source	SortedRL, arXiv 2603.23414v1 · Abstract, Section 2.2 and Figure 1(a), time in seconds
Review	checking…review by 2026-12-22 · standard cadence
Recorded changes	last 2026-10-05 · 3 revisions tracked
Claim id	of-compute-consumed-by-rollouts-at-16k-token

Where the guide uses it

1.4 Post-Training, Fine-Tuning & RL: The Hybrid Middle

← Full numbers register — every date-stamped figure in the guide, with revision history.