Will This Bug-Fixing Change Break Regression Testing?
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Context: Software source code is frequently changed for fixing revealed bugs. These bug-fixing changes might introduce unintended system behaviors, which are inconsistent with scenarios of existing regression test cases, and consequently break regression testing. For validating the quality of changes, regression testing is a required process before submitting changes during the development of software projects. Our pilot study shows that 48.7% bug-fixing changes might break regression testing at first run, which means developers have to run regression testing at least a couple of times for 48.7% changes. Such process can be tedious and time consuming. Thus, before running regression test suite, finding these changes and corresponding regression test cases could be helpful for developers to quickly fix these changes and improve the efficiency of regression testing. Goal: This paper proposes bug- fixing change impact prediction (BFCP), for predicting whether a bug-fixing change will break regression testing or not before running regression test cases, by mining software change histories. Method: Our approach employs the machine learning algorithms and static call graph analysis technique. Given a bug-fixing change, BFCP first predicts whether it will break existing regression test cases; second, if the change is predicted to break regression test cases, BFCP can further identify the might-be-broken test cases. Results: Results of experiments on 552 real bug-fixing changes from four large open source projects show that BFCP could achieve prediction precision up to 83.3%, recall up to 92.3%, and F-score up to 81.4%. For identifying the might-be-broken test cases, BFCP could achieve 100% recall.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it