Comparing Line and AST Granularity Level for Program Repair using PyGGI

Created by W.Langdon from gp-bibliography.bib Revision:1.4504

@InProceedings{An:2018:GI,
  author =       "Gabin An and Jinhan Kim and Shin Yoo",
  title =        "Comparing Line and {AST} Granularity Level for Program
                 Repair using {PyGGI}",
  booktitle =    "GI-2018, ICSE workshops proceedings",
  year =         "2018",
  editor =       "Justyna Petke and Kathryn Stolee and 
                 William B. Langdon and Westley Weimer",
  pages =        "19--26",
  address =      "Gothenburg, Sweden",
  month =        "2 " # jun,
  publisher =    "ACM",
  publisher_address = "New York, NY, USA",
  keywords =     "genetic algorithms, genetic programming, genetic
                 improvement, SBSE",
  isbn13 =       "978-1-4503-5753-1",
  URL =          "http://geneticimprovementofsoftware.com/wp-content/uploads/2018/04/An_2018_GI.pdf",
  DOI =          "doi:10.1145/3194810.3194814",
  size =         "8 pages",
  abstract =     "PyGGI is a lightweight Python framework that can be
                 used to implement generic Genetic Improvement
                 algorithms at the API level. The original version of
                 PyGGI only provided lexical modifications, i.e.,
                 modifications of the source code at the physical line
                 granularity level. This paper introduces new extensions
                 to PyGGI that enables syntactic modifications for
                 Python code, i.e., modifications that operates at the
                 AST granularity level. Taking advantage of the new
                 extensions, we also present a case study that compares
                 the lexical and syntactic search granularity level for
                 automated program repair, using ten seeded faults in a
                 real world open source Python project. The results show
                 that search landscapes at the AST granularity level are
                 more effective (i.e. eventually more likely to produce
                 plausible patches) due to the smaller sizes of
                 ingredient spaces (i.e., the space from which we search
                 for the material to build a patch), but may require
                 longer time for search because the larger number of
                 syntactically intact candidates leads to more fitness
                 evaluations.",
  notes =        "Slides:
                 http://geneticimprovementofsoftware.com/wp-content/uploads/2018/06/gi-pyggi.compressed.pdf

                 GI-2018 http://geneticimprovementofsoftware.com

                 part of \cite{Petke:2018:ICSEworkshop}",
}

Genetic Programming entries for Gabin An Jinhan Kim Shin Yoo

Citations