Learning to Predict Code Review Rounds in Modern Code Review Using Multi-Objective Genetic Programming
Bibliographic record
Abstract
Code review is an essential practice for software quality assurance. However, code review can be cumbersome as patches often undergo multiple rounds to fix bugs, enforce coding standards, and improve structure before merging or abandonment. Predicting the number of review rounds can help developers prioritize tasks and streamline the process. Existing machine learning models for review round prediction suffer from key limitations. Their black-box nature makes them difficult to interpret, reducing trust and adoption. Additionally, they rely on data re-balancing techniques that introduce artificial points, causing concept shifts and reducing reliability. To address these issues, we propose MORRP, a novel Multi-Objective Review Rounds Prediction approach. MORRP is based on Multi-Objective Genetic Programming (MOGP) to predict review rounds. Our method evolves interpretable models while optimizing precision, recall, and specificity without relying on data re-balancing. We evaluate our approach on three large open-source projects: Eclipse, OpenDaylight, and OpenStack. Results show that MORRP achieves competitive performance, with a micro F1 score between 0.65 and 0.75, outperforming complex ML models like Random Forest and LightGBM.
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 | 0.005 | 0.021 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 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".