RESTORE: Automated Regression Testing for Datasets
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
There has been a massive explosion of data generated by customers and retained by companies in the last decade. However, there is a significant mismatch between the increasing volume of data and the lack of automation methods and tools. The lack of best practices in data science programming may lead to software quality degradation, release schedule slippage, and budget overruns. To mitigate these concerns, we would like to bring software engineering best practices into data science. Specifically, we focus on automated data validation in the data preparation phase of the software development life cycle. This paper studies a real-world industrial case and applies software engineering best practices to develop an automated test harness called RESTORE. We release RESTORE as an open-source R package. Our experience report, done on the geodemographic data, shows that RESTORE enables efficient and effective detection of errors injected during the data preparation phase. RESTORE also significantly reduced the cost of testing. We hope that the community benefits from the open-source project and the practical advice based on our experience.
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 | 0.007 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.025 | 0.004 |
| Open science | 0.020 | 0.039 |
| 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 it