Merlin generates CodeQL queries from natural language questions via RAG-based iteration and a self-test technique using assistive queries, achieving 3.8x higher task accuracy and 31% less completion time in user studies while finding additional software issues.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
Interviews with nine data-intensive programmers identify three cross-cutting debugging challenges that visualization can address via evidence alignment, expectation comparison, and state tracing.
AlgoTouch constructs imperative programs incrementally by recording data transformations on an explicit notional machine and deterministically synthesizing control structures from observed execution traces.
A controlled user study with 24 programmers shows sketch-based pen input can handle breakpoint setting, step execution, and state inspection in debugging, though precision, recognition, and recall remain challenges.
citing papers explorer
-
Generating Complex Code Analyzers from Natural Language Questions
Merlin generates CodeQL queries from natural language questions via RAG-based iteration and a self-test technique using assistive queries, achieving 3.8x higher task accuracy and 31% less completion time in user studies while finding additional software issues.
-
Debugging as Evidence-Driven Reasoning: Visualization Opportunities in Data-Intensive Programming
Interviews with nine data-intensive programmers identify three cross-cutting debugging challenges that visualization can address via evidence alignment, expectation comparison, and state tracing.
-
AlgoTouch: An Execution-Centered Approach to Incremental Construction of Imperative Programs
AlgoTouch constructs imperative programs incrementally by recording data transformations on an explicit notional machine and deterministically synthesizing control structures from observed execution traces.
-
Sketch Bug: Using Sketch-Based Input for Interactive Code Debugging
A controlled user study with 24 programmers shows sketch-based pen input can handle breakpoint setting, step execution, and state inspection in debugging, though precision, recognition, and recall remain challenges.