On Cora, SGC and GCN have similar validation accuracy across 1-80 training examples per class; SGC is numerically higher through 40 examples and GCN is higher at 80. The prose specifically says SGC outperforms GCN with fewer than 5 samples.

On Cora, SGC and GCN have similar validation accuracy across 1-80 training examples per class; SGC is numerically higher through 40 examples and GCN is higher at 80. The prose specifically says SGC outperforms GCN with fewer than 5 samples. · CiteArk

Measurement results

0/12 assessed

0 supported0 disputed or conflicting12 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.
Reported	Latest observation	Evidence judgment
33.16%	—	Not assessed
32.94%	—	Not assessed
63.74%	—	Not assessed
60.68%	—	Not assessed
72.04%	—	Not assessed
71.46%	—	Not assessed
80.3%	—	Not assessed
80.16%	—	Not assessed
85.56%	—	Not assessed
85.38%	—	Not assessed
90.08%	—	Not assessed
90.44%	—	Not assessed

On Cora, SGC and GCN have similar validation accuracy across 1-80 training examples per class; SGC is numerically higher through 40 examples and GCN is higher at 80. The prose specifically says SGC outperforms GCN with fewer than 5 samples.

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results