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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 226–250 of 423 papers

TitleStatusHype
Compositional Generalization and Decomposition in Neural Program Synthesis—0
Efficient Pragmatic Program Synthesis with Informative Specifications—0
CodeGen: An Open Large Language Model for Code with Multi-Turn Program SynthesisCode6
CrossBeam: Learning to Search in Bottom-Up Program SynthesisCode1
Less is More: Summary of Long Instructions is Better for Program SynthesisCode1
Iterative Genetic Improvement: Scaling Stochastic Program Synthesis—0
Learning Program Synthesis for Integer Sequences from ScratchCode1
GPT-based Open-Ended Knowledge TracingCode1
Learning logic programs by discovering where not to searchCode0
SapientML: Synthesizing Machine Learning Pipelines by Learning from Human-Written Solutions—0
Explanatory Learning: Beyond Empiricism in Neural NetworksCode1
Synthesizing explainable counterfactual policies for algorithmic recourse with program synthesisCode0
MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem Solving—0
From Examples to Rules: Neural Guided Rule Synthesis for Information ExtractionCode1
A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human LevelCode1
Stress Rules from Surface Forms: Experiments with Program Synthesis—0
Differentiable Synthesis of Program Architectures—0
Automatic Synthesis of Diverse Weak Supervision Sources for Behavior AnalysisCode0
Solving Visual Analogies Using Neural Algorithmic Reasoning—0
Solving Probability and Statistics Problems by Program Synthesis—0
Solving Linear Algebra by Program Synthesis—0
Solving Linear Algebra by Program Synthesis—0
Solving Probability and Statistics Problems by Program Synthesis—0
Choose Your Programming Copilot: A Comparison of the Program Synthesis Performance of GitHub Copilot and Genetic Programming—0
Few-Shot Novel Concept Learning for Semantic Parsing—0
Show:102550
← PrevPage 10 of 17Next →
All datasetsSPoC TestPSPoC TestWAlgoLisp

Benchmark Results

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