abstract = "GenProg is a stochastic method based on genetic
programming that presents promising results in
automatic software repair via patch evolution.
GenProg's crossover operates on a patch representation
composed of high-granularity edits that indivisibly
comprise an edit operation, a faulty location, and a
fix statement used in replacement or insertions.
Recombination of such high-level minimal units limits
the technique's ability to effectively traverse and
recombine the repair search spaces. In this work, we
propose a reformulation of program repair operators
such that they explicitly traverse three subspaces that
underlie the search problem: Operator, Fault Space and
Fix Space. We leverage this reformulation in the form
of new crossover operators that faithfully respect this
subspace division, improving search performance. Our
experiments on 43 programs validate our insight, and
show that the Unif1Space without memorization performed
best, improving the fix rate by 34percent.",
notes = "Fig 2 representation where parts of patch are placed
together versus whole of patch being adjacent. gcd,
zune, checksum, digits, grade, median, smallest,
syllables.