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 401–423 of 423 papers

TitleStatusHype
Dynamic Neural Program Embeddings for Program Repair—0
Code Synthesis with Priority Queue Training—0
Neural Program Search: Solving Data Processing Tasks from Description and Examples—0
Learning to select examples for program synthesis—0
Dynamic Neural Program Embedding for Program RepairCode0
Selecting Representative Examples for Program SynthesisCode0
Glass-Box Program Synthesis: A Machine Learning Approach—0
A probabilistic and multi-objective analysis of lexicase selection and epsilon-lexicase selectionCode0
Learning to Infer Graphics Programs from Hand-Drawn ImagesCode0
P-Tree ProgrammingCode0
LoopInvGen: A Loop Invariant Generator based on Precondition Inference—0
Learning Disjunctions of Predicates—0
Towards Synthesizing Complex Programs from Input-Output Examples—0
Synthesizing Imperative Programs from Examples Guided by Static Analysis—0
Summary - TerpreT: A Probabilistic Programming Language for Program Induction—0
Sampling for Bayesian Program Learning—0
Time Series Structure Discovery via Probabilistic Program Synthesis—0
DeepCoder: Learning to Write ProgramsCode0
Latent Attention For If-Then Program Synthesis—0
Differentiable Functional Program InterpretersCode0
Neuro-Symbolic Program Synthesis—0
TerpreT: A Probabilistic Programming Language for Program Induction—0
Unsupervised Learning by Program Synthesis—0
Show:102550
← PrevPage 9 of 9Next →

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