DIRTY studies learned predictions of variable names and types for decompiler output. It addresses readability and analyst comprehension, rather than recovery of the original symbols with certainty. Use it when evaluating how much a suggested name helps navigate code, then verify any semantic interpretation against uses, data flow and observed behavior before adopting it as a fact.
What the result means
A plausible name is an annotation hypothesis. Check where the variable is written and read, and keep the original decompiler identifier available so later evidence can reverse a mistaken rename.
Research context
The USENIX Security publication is the primary record for the paper. Its evaluation should be read in the context of its dataset and decompiler settings before applying it to a different target.
Requirements & evidence
- Resource type
- Paper
- Category
- Unknown
- Host platforms
- Unknown
- Targets
- Unknown
- Level
- Unknown
- Author(s)
- Qibin Chen, Jeremy Lacomis, Edward J. Schwartz, Claire Le Goues, Graham Neubig, Bogdan Vasilescu
- Year
- 2022
- Venue
- USENIX Security 2022
- Current version
- Unknown
- Version date
- 2022-08
- Topic
- DIRTY predicts useful names and types for decompiler output
- Source checked
- 2026-11-03T10:44:21.206859+00:00
Unknown fields have not been established by an author or publisher source.
Primary sources
Source descriptions establish documented scope. They do not establish that every workflow has been reproduced by AI Craft Pad.