Locating Latent Design Information in Developer Discussions: A Study on Pull Requests
Bibliographic record
Abstract
A software system's design determines many of its properties, such as maintainability and performance. An understanding of design is needed to maintain system properties as changes to the system occur. Unfortunately, many systems do not have up-to-date design documentation and approaches that have been developed to recover design often focus on how a system works by extracting structural and behaviour information rather than information about the desired design properties, such as robustness or performance. In this paper, we explore whether it is possible to automatically locate where design is discussed in on-line developer discussions. We investigate and introduce a classifier that can locate paragraphs in pull request discussions that pertain to design with an average AUC score of 0.87. We show that this classifier, when applied to projects on which it was not trained, agrees with the identification of design points by humans with an average AUC score of 0.79. We describe how this classifier could be used as the basis of tools to improve such tasks as reviewing code and implementing new features.
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 | 0.009 | 0.098 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.004 | 0.003 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.002 | 0.004 |
| Open science | 0.001 | 0.002 |
| 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".