Predicting Stability of Open-Source Software Systems Using Combination of Bayesian Classifiers
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
The use of free and Open-Source Software (OSS) systems is gaining momentum. Organizations are also now adopting OSS, despite some reservations, particularly about the quality issues. Stability of software is one of the main features in software quality management that needs to be understood and accurately predicted. It deals with the impact resulting from software changes and argues that stable components lead to a cost-effective software evolution. Changes are most common phenomena present in OSS in comparison to proprietary software. This makes OSS system evolution a rich context to study and predict stability. Our objective in this work is to build stability prediction models that are not only accurate but also interpretable, that is, able to explain the link between the architectural aspects of a software component and its stability behavior in the context of OSS. Therefore, we propose a new approach based on classifiers combination capable of preserving prediction interpretability. Our approach is classifier-structure dependent. Therefore, we propose a particular solution for combining Bayesian classifiers in order to derive a more accurate composite classifier that preserves interpretability. This solution is implemented using a genetic algorithm and applied in the context of an OSS large-scale system, namely the standard Java API. The empirical results show that our approach outperforms state-of-the-art approaches from both machine learning and software engineering.
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 | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.003 |
| Open science | 0.002 | 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