Across 10 random Cora training splits with fixed validation and test sets, SGC reports 80.62% test accuracy, close to GCN's 80.53%; GAT is highest among the listed models at 82.29%.

Across 10 random Cora training splits with fixed validation and test sets, SGC reports 80.62% test accuracy, close to GCN's 80.53%; GAT is highest among the listed models at 82.29%. · 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: 1.4	80.53%	—	Not assessed
reportedPlusMinus: 1.24	76.94%	—	Not assessed
reportedPlusMinus: 4.5	74.23%	—	Not assessed
reportedPlusMinus: 1.45	72.68%	—	Not assessed
reportedPlusMinus: 1.16	82.29%	—	Not assessed
reportedPlusMinus: 1.21	80.62%	—	Not assessed

Across 10 random Cora training splits with fixed validation and test sets, SGC reports 80.62% test accuracy, close to GCN's 80.53%; GAT is highest among the listed models at 82.29%.

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results