JITAtlas: Checking Lifetime and Protection Obligations in Compiler Rewrites

Compiler rewrites can preserve returned values while violating object lifetime or ownership. Such failures arise when a rewrite changes when an object remains live, whether a borrowed pointer stays supported, or what ownership reaches the caller. We present JITAtlas, a source-level checker that reconstructs reference and target computations from optimizer code and checks valid uses, continuous borrow support, and caller-visible ownership. On a 58-input benchmark constructed and labeled independently of JITAtlas output, JITAtlas detects all 29 defects and reports none of 29 safe inputs; PyRefcon detects 20 defects and CpyChecker 18. Across three CPython snapshots, JITAtlas extracts 3,332 rewrite alternatives, retains 801 under recovered receiving contexts, and reports 194 violations. Manual review confirms 92 reports, giving 47.42% precision. End-to-end analysis takes 35.56-42.31 s per snapshot. JITAtlas further identifies 15 new bugs across five failure classes, each with a reproducible proof of concept.

Authors

Institutions

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-18
DOI
https://doi.org/10.48550/arxiv.2611.23715
Primary Topic
Software Testing and Debugging Techniques
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

JITAtlas: Checking Lifetime and Protection Obligations in Compiler Rewrites

Baihong Chen, Wen Li
arXiv (Cornell University)
Software Testing and Debugging Techniques
preprint

JITAtlas: Checking Lifetime and Protection Obligations in Compiler Rewrites

Baihong Chen, Wen Li
preprint en

Abstract

Compiler rewrites can preserve returned values while violating object lifetime or ownership. Such failures arise when a rewrite changes when an object remains live, whether a borrowed pointer stays supported, or what ownership reaches the caller. We present JITAtlas, a source-level checker that reconstructs reference and target computations from optimizer code and checks valid uses, continuous borrow support, and caller-visible ownership. On a 58-input benchmark constructed and labeled independently of JITAtlas output, JITAtlas detects all 29 defects and reports none of 29 safe inputs; PyRefcon detects 20 defects and CpyChecker 18. Across three CPython snapshots, JITAtlas extracts 3,332 rewrite alternatives, retains 801 under recovered receiving contexts, and reports 194 violations. Manual review confirms 92 reports, giving 47.42% precision. End-to-end analysis takes 35.56-42.31 s per snapshot. JITAtlas further identifies 15 new bugs across five failure classes, each with a reproducible proof of concept.

arXiv (Cornell University)
Utah State University (US)
Software Testing and Debugging Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon