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

Measurement results

0/6 assessed

0 supported0 disputed or conflicting6 not assessed

The complete result group stays with its claim. Assessed rows come first; their judgments do not replace the whole-claim conclusion. Expand a row for conditions, sources, and evidence history.

Each row is a measurement with its reported value, latest available observation, and cumulative evidence state.
Metric and conditions	Reported	Latest observation	Evidence judgment
reportedPlusMinus: 2.95	77.09%	—	Not assessed
reportedPlusMinus: 2.19	74.46%	—	Not assessed
reportedPlusMinus: 2.03	77.2%	—	Not assessed
reportedPlusMinus: 1.76	77.53%	—	Not assessed
reportedPlusMinus: 1.41	78.79%	—	Not assessed
reportedPlusMinus: 1.62	77.02%	—	Not assessed

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%.

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results