kirancodes.me
To Proof Maintenance & Beyond!
FSE 2021

A replication of 'DeepBugs: a learning approach to name-based bug detection'

Jordan Winkler, Abhimanyu Agarwal, Caleb Tung, Dario Rios Ugalde, Young Jin Jung, James C. Davis

PDFDOI 10.1145/3468264.3477221dblp

Abstract

We replicated the main result of DeepBugs, a bug detection algorithm for name-based bugs. The original authors evaluated it in three contexts: swapped-argument bugs, wrong binary operator,and wrong binary operator operands. We followed the algorithm and replicated the results for swapped-argument bugs. Our replication used independent implementations of the major components: training set generation, token vectorization, and neural network data pipeline, model, and loss function. Using the same dataset and the same testing process, we report comparable performance: within 2% of the accuracy reported by Pradel and Sen.

BibTeX
@inproceedings{Winkler-al:FSE21,
  author    = {Jordan Winkler and
               Abhimanyu Agarwal and
               Caleb Tung and
               Dario Rios Ugalde and
               Young Jin Jung and
               James C. Davis},
  title     = {A replication of {'DeepBugs:} a learning approach to name-based bug detection'},
  booktitle = {{ESEC/SIGSOFT} {FSE}},
  pages     = {1604},
  publisher = {{ACM}},
  year      = {2021},
}

Related papers