The relationship between commit message detail and defect proneness in Java projects on GitHub
Bibliographic record
Abstract
Just-In-Time (JIT) defect prediction models aim to predict the commits that will introduce defects in the future. Traditionally, JIT defect prediction models are trained using metrics that are primarily derived from aspects of the code change itself (e.g., the size of the change, the author's prior experience). In addition to the code that is submitted during a commit, authors write commit messages, which describe the commit for archival purposes. It is our position that the level of detail in these commit messages can provide additional explanatory power to JIT defect prediction models. Hence, in this paper, we analyze the relationship between the defect proneness of commits and commit message volume (i.e., the length of the commit message) and commit message content (approximated using spam filtering technology). Through analysis of JIT models that were trained using 342 GitHub repositories, we find that our JIT models outperform random guessing models, achieving AUC and Brier scores that range between 0.63-0.96 and 0.01-0.21, respectively. Furthermore, our metrics that are derived from commit message detail provide a statistically significant boost to the explanatory power to the JIT models in 43%-80% of the studied systems, accounting for up to 72% of the explanatory power. Future JIT studies should consider adding commit message detail metrics.
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.
How this classification was reachedexpand
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".