Program Boosting: Program Synthesis via Crowd-Sourcing

Created by W.Langdon from gp-bibliography.bib Revision:1.4333

  author =       "Robert A. Cochran and Loris D'Antoni and 
                 Benjamin Livshits and David Molnar and Margus Veanes",
  title =        "Program Boosting: Program Synthesis via
  booktitle =    "Proceedings of the 42nd Annual ACM SIGPLAN-SIGACT
                 Symposium on Principles of Programming Languages, POPL
  year =         "2015",
  editor =       "Andy Gill",
  pages =        "677--688",
  address =      "Mumbai, India",
  publisher_address = "New York, NY, USA",
  month =        "15-17 " # jan,
  publisher =    "ACM",
  keywords =     "genetic algorithms, genetic programming,
                 crowd-sourcing, program synthesis, regular expressions,
                 symbolic automata SFA",
  isbn13 =       "978-1-4503-3300-9",
  acmid =        "2676973",
  URL =          "",
  URL =          "",
  DOI =          "doi:10.1145/2676726.2676973",
  size =         "12",
  abstract =     "In this paper, we investigate an approach to program
                 synthesis that is based on crowd-sourcing. With the
                 help of crowd-sourcing, we aim to capture the wisdom of
                 the crowds to find good if not perfect solutions to
                 inherently tricky programming tasks, which elude even
                 expert developers and lack an easy-to-formalize

                 We propose an approach we call program boosting, which
                 involves crowd-sourcing imperfect solutions to a
                 difficult programming problem from developers and then
                 blending these programs together in a way that improves
                 their correctness.

                 We implement this approach in a system called
                 CROWDBOOST and show in our experiments that interesting
                 and highly non-trivial tasks such as writing regular
                 expressions for URLs or email addresses can be
                 effectively crowd-sourced. We demonstrate that
                 carefully blending the crowd-sourced results together
                 consistently produces a boost, yielding results that
                 are better than any of the starting programs. Our
                 experiments on 465 program pairs show consistent boosts
                 in accuracy and demonstrate that program boosting can
                 be performed at a relatively modest monetary cost.",
  notes =        "Amazon mechanical turk mturk. UTF-16, email addresses,
                 URLs, dates, USA telephone numbers.

                 Also known as

                 Also available as ACM Sigplan Notices 50(1) Jan 2015
                 677-688, ISSN:0362-1340",

Genetic Programming entries for Robert A Cochran Loris D'Antoni Benjamin Livshits David Molnar Margus Veanes