Characterizing Task-Relevant Information in Natural Language Software Artifacts
Bibliographic record
Abstract
To complete a software development task, a software developer often consults artifacts which mostly consist of natural language text, such as API documentation, bug reports, and Q&A forums. Not all information within these artifacts is relevant to a developer's current task, forcing them to filter through large amounts of irrelevant information, a frustrating and time-consuming activity. Since failing to locate relevant information may lead developers to incorrect or incomplete solutions, many approaches attempt to automatically extract relevant information from natural language artifacts. However, existing approaches are able to identify relevant text only for certain types of tasks and artifacts. To explore how these limitations could be relaxed, we conducted a controlled experiment in which we asked 20 software developers to examine 20 natural language artifacts consisting of 1,874 sentences and highlight the text they considered relevant to six software development tasks. Although the 2,463 distinct highlights participants created indicate variability in the perceived relevance of the text, the information considered key to completing the tasks was consistent. We observe consistency in the text using frame semantics, an approach that captures the key meaning of sentences, suggesting that frame semantics can be used in the future to automatically identify task-relevant information in natural language artifacts.
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 | 0.065 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".