HyperAI超神经

Defect Detection On Codexglue Devign

评估指标

Accuracy

评测结果

各个模型在此基准测试上的表现结果

		Paper Title
CodeT5	65.78	CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation
CodeT5-base + GFSA	64.75	Graph Convolutions Enrich the Self-Attention in Transformers!
CodeBERT + GFSA	64.49	Graph Convolutions Enrich the Self-Attention in Transformers!
RoBERTa + GFSA	64.39	Graph Convolutions Enrich the Self-Attention in Transformers!
CodeBERT	64.31	Graph Convolutions Enrich the Self-Attention in Transformers!
CodeT5-small + GFSA	63.69	Graph Convolutions Enrich the Self-Attention in Transformers!
CodeT5-base	63.51	Graph Convolutions Enrich the Self-Attention in Transformers!
CodeT5-small	63.25	Graph Convolutions Enrich the Self-Attention in Transformers!
PLBART + GFSA	62.96	Graph Convolutions Enrich the Self-Attention in Transformers!
RoBERTa	62.88	Graph Convolutions Enrich the Self-Attention in Transformers!
PLBART	62.63	Graph Convolutions Enrich the Self-Attention in Transformers!
CodeBERT	62.08	CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation

0 of 12 row(s) selected.

HyperAI超神经

Defect Detection On Codexglue Devign

评估指标

Accuracy

评测结果

各个模型在此基准测试上的表现结果

		Paper Title
CodeT5	65.78	CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation
CodeT5-base + GFSA	64.75	Graph Convolutions Enrich the Self-Attention in Transformers!
CodeBERT + GFSA	64.49	Graph Convolutions Enrich the Self-Attention in Transformers!
RoBERTa + GFSA	64.39	Graph Convolutions Enrich the Self-Attention in Transformers!
CodeBERT	64.31	Graph Convolutions Enrich the Self-Attention in Transformers!
CodeT5-small + GFSA	63.69	Graph Convolutions Enrich the Self-Attention in Transformers!
CodeT5-base	63.51	Graph Convolutions Enrich the Self-Attention in Transformers!
CodeT5-small	63.25	Graph Convolutions Enrich the Self-Attention in Transformers!
PLBART + GFSA	62.96	Graph Convolutions Enrich the Self-Attention in Transformers!
RoBERTa	62.88	Graph Convolutions Enrich the Self-Attention in Transformers!
PLBART	62.63	Graph Convolutions Enrich the Self-Attention in Transformers!
CodeBERT	62.08	CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation

0 of 12 row(s) selected.

Defect Detection On Codexglue Devign | SOTA | HyperAI超神经