Across 10 random Pubmed training splits with fixed validation and test sets, SGC reports 77.02% test accuracy, close to GCN's 77.09%; GAT is highest among the listed models at 78.79%.

Across 10 random Pubmed training splits with fixed validation and test sets, SGC reports 77.02% test accuracy, close to GCN's 77.09%; GAT is highest among the listed models at 78.79%. · 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: 2.95	77.09%	—	尚未评估
reportedPlusMinus: 2.19	74.46%	—	尚未评估
reportedPlusMinus: 2.03	77.2%	—	尚未评估
reportedPlusMinus: 1.76	77.53%	—	尚未评估
reportedPlusMinus: 1.41	78.79%	—	尚未评估
reportedPlusMinus: 1.62	77.02%	—	尚未评估

Across 10 random Pubmed training splits with fixed validation and test sets, SGC reports 77.02% test accuracy, close to GCN's 77.09%; GAT is highest among the listed models at 78.79%.

报告指标与观测值

Assessment（0）

关联运行（0）

测量结果