Across 10 random Citeseer training splits with fixed validation and test sets, SGC reports 71.40% test accuracy; GAT reports 72.6%, while SGC's reported variation is the largest among the listed non-daggered models.

Across 10 random Citeseer training splits with fixed validation and test sets, SGC reports 71.40% test accuracy; GAT reports 72.6%, while SGC's reported variation is the largest among the listed non-daggered models. · CiteArk

测量结果

已评估 0/6 项

获得支持 0有争议或冲突 0尚未评估 6

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
reportedPlusMinus: 2.9	70.67%	—	尚未评估
reportedPlusMinus: 2.27	66.56%	—	尚未评估
reportedPlusMinus: 0.81	67.26%	—	尚未评估
reportedPlusMinus: 0.95	71.04%	—	尚未评估
reportedPlusMinus: 0.58	72.6%	—	尚未评估
reportedPlusMinus: 3.92	71.4%	—	尚未评估

Across 10 random Citeseer training splits with fixed validation and test sets, SGC reports 71.40% test accuracy; GAT reports 72.6%, while SGC's reported variation is the largest among the listed non-daggered models.

报告指标与观测值

Assessment（0）

关联运行（0）

测量结果