[Journal First] Inference of Development Activities from Interaction with Uninstrumented Applications
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
This paper is published in Journal of Empirical Software Engineering (DOI: 10.1007/s10664-017-9547-8). Studying developers' behavior is crucial for designing effective techniques and tools to support developers' daily work. However, there are two challenges in collecting and analyzing developers' behavior data. First, instrumenting many software tools commonly used in real work settings (e.g., IDEs, web browsers) is difficult and requires significant resources. Second, the collected behavior data consist of low-level and fine-grained event sequences, which must be abstracted into high-level development activities for further analysis. To address these two challenges, we first use our ActivitySpace framework to improve the generalizability of the data collection. Then, we propose a Condition Random Field (CRF) based approach to segment and label the developers' low-level actions into a set of basic, yet meaningful development activities. To evaluate our proposed approach, we deploy the ActivitySpace framework in an industry partner's company and collect the real working data from ten professional developers' one-week work. We conduct an experiment with the collected data and a small number of initial human-labeled training data using the CRF model and the other three baselines (i.e., a heuristic-rules based method, a SVM classifier, and a random weighted classifier). The proposed CRF model achieves better performance (i.e., 0.728 accuracy and 0.672 macro-averaged F1-score) than the other three baselines.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 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