After general post-training, the 4.5T OLMo3-32B checkpoint is more robust to prefilling attacks than the 4.9T checkpoint (53% versus 21%). The expanded comparison also favors the selected intermediate checkpoint over the final pretraining and mid-training checkpoints.

After general post-training, the 4.5T OLMo3-32B checkpoint is more robust to prefilling attacks than the 4.9T checkpoint (53% versus 21%). The expanded comparison also favors the selected intermediate checkpoint over the final pretraining and mid-training checkpoints. · CiteArk

Measurement results

0/2 assessed

0 supported0 disputed or conflicting2 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
posttraining: General post-training · basePretrainingTokensTrillions: 4.5	53%	—	Not assessed
posttraining: General post-training · basePretrainingTokensTrillions: 4.9	21%	—	Not assessed

After general post-training, the 4.5T OLMo3-32B checkpoint is more robust to prefilling attacks than the 4.9T checkpoint (53% versus 21%). The expanded comparison also favors the selected intermediate checkpoint over the final pretraining and mid-training checkpoints.

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results