Full downstream results after standard 4-stage post-training pipeline (SFT, DPO, RLVR1, RLVR2) for 7B TRKD post-training performance.

Full downstream results after standard 4-stage post-training pipeline (SFT, DPO, RLVR1, RLVR2) for 7B TRKD post-training performance. · CiteArk

已评估 0/16 项

获得支持 0有争议或冲突 0尚未评估 16

保留同一结论下的完整结果组。已有评估排在前面；单项判断不替代整组结论。展开行查看条件、来源与历次证据。

每行是一项测量，分别显示论文报告、最近可用实测和累计证据状态。
论文报告	最近可用实测	证据判断
70.7 percentage_points	—	尚未评估
52.9 percentage_points	—	尚未评估
46.3 percentage_points	—	尚未评估
31.8 percentage_points	—	尚未评估
36.8 percentage_points	—	尚未评估
14.4 percentage_points	—	尚未评估
51.7 percentage_points	—	尚未评估
22.3 percentage_points	—	尚未评估
8 percentage_points	—	尚未评估
40.9 percentage_points	—	尚未评估
17.4 percentage_points	—	尚未评估
59 percentage_points	—	尚未评估

报告指标与观测值