Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Bug Identification on Bounce Tail Student Programs 146K submissions, 108,583 unique
Loading...
94
Accuracy
Contrastive HoareLSTM + PTW
48.24
60.12
72
83.88
Oct 27, 2021
Accuracy
Precision (Correct Program)
Recall (Correct Program)
Precision (Broken Program)
Recall (Broken Program)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Precision (Correct Program)
Recall (Correct Program)
Precision (Broken Program)
Recall (Broken Program)
Contrastive HoareLSTM + PTW
sampling_agent=pre-tra...
2021.10
94
91
97.6
97.4
90.4
Code-as-text
2021.10
68.4
85.9
44
62.4
92.8
Majority Class
2021.10
50
-
-
-
-
Feedback
Search any
task
Search any
task