Knowledge Distillation During Mid-Training Favors Reasoning over Factual Recall
尚未评估计划受阻研究发现claim_fig3_top1_agreement_entropy
Lower teacher predictive entropy corresponds to substantially higher teacher top-1 agreement with the ground-truth token across all data domains and teacher sizes.
来源：source_paper:Figure 3, Page 5
报告指标与观测值
这条 Claim 暂无结构化指标。
Assessment（0）
这条 Claim 暂无已发布的不可变 Assessment。
关联运行（0）
这条 Claim 暂无关联执行。