[Retracted] A Deep Learning Approach for a Source Code Detection Model Using Self-Attention

Table 2

Statistics of datasets used for clone detection.

Dataset	OJClone	BigCloneBench
Code fragments	7500	59688
True clone pairs (percentage)	6.8	95.6
Avg tokens	232	228
Avg AST depth	12.9	9.8
Avg AST nodes	184	205