Research domain
Code & Developer AI
Verilog Syntax Generation5 benchmarks · 1 papersRTL-to-GDSII flow automation5 benchmarks · 1 papersText2Cypher5 benchmarks · 2 paperstask generation5 benchmarks · 2 papersWindow-level anti-pattern detection5 benchmarks · 1 papersTest Generation5 benchmarks · 4 papersAdversarial Code Compliance5 benchmarks · 1 papersCompetitive Coding5 benchmarks · 1 papersRace Condition Detection5 benchmarks · 1 papersError Localization5 benchmarks · 2 papersCUDA Kernel Generation5 benchmarks · 2 papersVulnerability Prediction5 benchmarks · 3 papersSoftware Engineering Problem Solving5 benchmarks · 5 papersCompiler Fuzzing5 benchmarks · 1 papersCoding Agent5 benchmarks · 2 papersLogic program generation5 benchmarks · 1 papersPre-load security auditing5 benchmarks · 1 papersWorkflow Reconstruction5 benchmarks · 1 papersCounterexample generation5 benchmarks · 2 papersVulnerability Exploit Generation5 benchmarks · 1 papersResearch Replication5 benchmarks · 2 papersCode Correctness Prediction5 benchmarks · 1 papersinductive Prolog rule synthesis5 benchmarks · 1 papersNL-to-Scala5 benchmarks · 1 papersScript Generation5 benchmarks · 3 papersCoding Ability5 benchmarks · 3 papersMalicious code detection5 benchmarks · 3 papersCode Debugging5 benchmarks · 4 papersPatch-state classification5 benchmarks · 1 papersFile-level Localization5 benchmarks · 4 papersVulnerability Reproduction5 benchmarks · 5 papersBinary Function Retrieval5 benchmarks · 2 papers