Full downstream results after standard 4-stage post-training pipeline (SFT, DPO, RLVR1, RLVR2) for 13B RKD post-training performance.

Full downstream results after standard 4-stage post-training pipeline (SFT, DPO, RLVR1, RLVR2) for 13B RKD post-training performance. · CiteArk

Measurement results

0/16 assessed

0 supported0 disputed or conflicting16 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
75.1 percentage_points	—	Not assessed
58.1 percentage_points	—	Not assessed
49.3 percentage_points	—	Not assessed
33.3 percentage_points	—	Not assessed
38.7 percentage_points	—	Not assessed
16 percentage_points	—	Not assessed
53.9 percentage_points	—	Not assessed
22.3 percentage_points	—	Not assessed
7.7 percentage_points	—	Not assessed
38.2 percentage_points	—	Not assessed
17 percentage_points	—	Not assessed
56 percentage_points	—	Not assessed

Full downstream results after standard 4-stage post-training pipeline (SFT, DPO, RLVR1, RLVR2) for 13B RKD post-training performance.

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results