Detecting and Fixing API Misuses of Data Science Libraries Using Large Language Models
Bibliographic record
Abstract
Data science libraries, such as scikit-learn and pandas, specialize in processing and manipulating data. The data-centric nature of these libraries makes the detection of API misuse in them more challenging. This paper introduces DSCHECKER, an LLM-based approach designed for detecting and fixing API misuses of data science libraries. We identify two key pieces of information, API directives and data information, that may be beneficial for API misuse detection and fixing. Using three LLMs and misuses from five data science libraries, we experiment with various prompts. We find that incorporating API directives and data-specific details enhances DSCHECKER's ability to detect and fix API misuses, with the best-performing model achieving a detection <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$F_{1}$</tex>-score of 61.18% and fixing 51.28% of the misuses. Building on these results, we implement DSCHECKER <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">${ }_{\text {agent }}$</tex> which includes an adaptive function calling mechanism to access information on demand, simulating a realworld setting where information about the misuse is unknown in advance. We find that DSCHECKER <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">${ }_{\text {agent }}$</tex> achieves 48.65% detection <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$F_{1}$</tex>-score and fixes 39.47% of the misuses, demonstrating the promise of LLM-based API misuse detection and fixing in real-world scenarios.
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 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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.014 |
| Open science | 0.003 | 0.009 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".