SOTAVerified

Program Synthesis

Program synthesis is the process of automatically generating a program or code snippet that satisfies a given specification or set of requirements. This can include generating code from a formal specification, a natural language description, or example inputs and outputs. The primary goal of program synthesis is to minimize human intervention in the coding process, reduce errors, and improve productivity.

Program synthesis often involves the use of advanced algorithms, artificial intelligence, and machine learning techniques to search the space of possible programs that meet the given constraints. This process can be guided by a variety of techniques, such as constraint solving, symbolic execution, and genetic algorithms.

Papers

Showing 241250 of 423 papers

TitleStatusHype
Stress Rules from Surface Forms: Experiments with Program Synthesis0
Differentiable Synthesis of Program Architectures0
Automatic Synthesis of Diverse Weak Supervision Sources for Behavior AnalysisCode0
Solving Visual Analogies Using Neural Algorithmic Reasoning0
Solving Probability and Statistics Problems by Program Synthesis0
Solving Linear Algebra by Program Synthesis0
Solving Linear Algebra by Program Synthesis0
Solving Probability and Statistics Problems by Program Synthesis0
Choose Your Programming Copilot: A Comparison of the Program Synthesis Performance of GitHub Copilot and Genetic Programming0
Few-Shot Novel Concept Learning for Semantic Parsing0
Show:102550
← PrevPage 25 of 43Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DrRepairSuccess rate @budget 10038.5Unverified
2Multiclass localizerSuccess rate @budget 10034.2Unverified
#ModelMetricClaimedVerifiedStatus
1DrRepairSuccess rate @budget 10057Unverified
2Multiclass localizerSuccess rate @budget 10053.7Unverified
#ModelMetricClaimedVerifiedStatus
1CodeTrans-MT-TF-SmallAccuracy90.31Unverified