Empirical study using expert Delphi consensus and student tasks finds input-output question proxies and response-time measures more reliable for code comprehension than syntax-based ones.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.SE 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
LLM-generated code matches human-written code in overall readability but exhibits different issue patterns, and prompt engineering has limited impact on improving it.
citing papers explorer
-
On the Reliability of Code Comprehension Proxies
Empirical study using expert Delphi consensus and student tasks finds input-output question proxies and response-time measures more reliable for code comprehension than syntax-based ones.
-
The Readability Spectrum: Patterns, Issues, and Prompt Effects in LLM-Generated Code
LLM-generated code matches human-written code in overall readability but exhibits different issue patterns, and prompt engineering has limited impact on improving it.