Across MATH-500 and Countdown for SPG and GDPO, IM produces a higher (less negative) mean sample-level ELBO and a lower average within-batch standard deviation. The reported mean-ELBO lift is larger on Countdown than on MATH-500 for both frameworks.

Across MATH-500 and Countdown for SPG and GDPO, IM produces a higher (less negative) mean sample-level ELBO and a lower average within-batch standard deviation. The reported mean-ELBO lift is larger on Countdown than on MATH-500 for both frameworks. · CiteArk

测量结果

已评估 0/20 项

获得支持 0有争议或冲突 0尚未评估 20

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。
指标与条件	论文报告	最近可用实测	证据判断
model: SPG · dataset: MATH-500	-2.2864 ELBO units	—	尚未评估
model: SPG · dataset: MATH-500	0.947 ELBO units	—	尚未评估
model: SPG+IM · dataset: MATH-500	-2.2146 ELBO units	—	尚未评估
model: SPG+IM · dataset: MATH-500	0.9085 ELBO units	—	尚未评估
model: GDPO · dataset: MATH-500	-2.1095 ELBO units	—	尚未评估
model: GDPO · dataset: MATH-500	1.1245 ELBO units	—	尚未评估
model: GDPO+IM · dataset: MATH-500	-2.0731 ELBO units	—	尚未评估
model: GDPO+IM · dataset: MATH-500	0.9236 ELBO units	—	尚未评估
model: SPG · dataset: Countdown	-1.8889 ELBO units	—	尚未评估
model: SPG · dataset: Countdown	1.3627 ELBO units	—	尚未评估
model: SPG+IM · dataset: Countdown	-1.6249 ELBO units	—	尚未评估
model: SPG+IM · dataset: Countdown	1.0596 ELBO units	—	尚未评估

Across MATH-500 and Countdown for SPG and GDPO, IM produces a higher (less negative) mean sample-level ELBO and a lower average within-batch standard deviation. The reported mean-ELBO lift is larger on Countdown than on MATH-500 for both frameworks.

报告指标与观测值

Assessment（0）

关联运行（0）

测量结果