Identifying Candidate Classes for Unit Testing Using Deep Learning Classifiers: An Empirical Validation
Bibliographic record
Abstract
This paper aims at investigating the use of deep learning to suggest (prioritize) classes to be tested rigorously during unit testing of object-oriented systems. We relied on software unit testing information history and source code metrics. We conducted an empirical study using data collected from two Apache open-source Java software systems (POI and ANT). For each software system, we extracted the source code of five different versions. For each version, we collected various metrics from the source code of the Java classes. Then, for all software classes, we extracted testing coverage measures at instruction and method levels of granularity. We used the existing JUnit test cases developed for these systems. Based on the different datasets we collected, we trained several deep neural network models. We validated the obtained classifiers using four validation techniques: (1) CV: Cross Version validation, (2) CPV: Combined Previous Version validation, (3) CSPV: Combined System and Previous Version validation, and (4) LOSO: Leave One System Out validation. The obtained results in terms of classifiers’ performance vary between 70% and 80% of accuracy and strongly support the viability of our approach.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.011 | 0.042 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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 source (direct Gemma or distilled Codex), 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".