Pandas has emerged as the de facto library for data processing and machine learning, widely used for tasks, such as data loading, transformation, and analysis. Despite its ubiquity, there has been limited systematic investigation into how Pandas is used in real-world projects and how typical workflows are composed in practice. To address this gap, we introduce PandasCorpus, a dataset curated from GitHub repositories that captures real-world Pandas workflows at scale. In this work, a workflow refers to Pandas-based code contained in Jupyter notebooks, a prevalent medium for writing, executing, and sharing data analysis code. The dataset comprises 139k notebooks from approximately 100k repositories and captures more than 4M Pandas API calls spanning 136 distinct operations. Beyond dataset construction, we characterize workflows using structural and Pandas-specific features and analyze notebook evolution between 2015 and 2025. Our study examines code executability, notebook size, and recurring sequences of Pandas operations, providing empirical insights into how Pandas is used in practice. The resulting corpus offers a reusable resource for studying data analysis workflows, Pandas usage patterns, and library-aware code composition. Both the dataset and the extraction pipeline are publicly available via GitHub and Zenodo.
Lisa Taldir, Muhammad Ahmad Saeed, David Defour +2cs.AI
This paper investigates the capability of Large Language Models (LLMs) to detect and classify floating-point errors statically in software code. We introduce InterFLOPBench, a benchmark of 90 C kernels with 1 130 test samples designed to evaluate LLMs across six categories of floating-point error: cancellation, comparison, division by zero, overflow, underflow and NaN, compared across 14 LLMs. The evaluation framework treats floating-point error detection as a multi-label classification problem and employs the F1-score metric to measure performance. Results demonstrate that latest models (Qwen 3 32b, Gemini 2.5 Flash, Phi 4 Reasoning, DeepSeek R1T2, and gpt-oss 20b and 120b) achieve a performance greater than 0.88 overall F1-score. Performance varies between error categories, between explicit operations such as division by zero (Average F1-score: 0.8479) and more subtle numerical phenomena such as underflow (Average F1-score: 0.6059) and cancellation (Average F1-score: 0.6164).
This paper investigates rubric-aware, multitask fine-tuning of transformer models for automated grading of introductory C++ programming assignments, with the goal of producing grade predictions that better reflect instructor grading behavior than general-purpose LLMs. Using multi-semester CS1 data, student submissions are paired with numeric scores, letter-grade buckets, and assignment rubrics, then preprocessed into unified sequences for transformer input. A BART encoder-decoder with LoRA adaptation is trained to jointly predict numeric grades and grade buckets, augmented with a distribution-matching term to align predicted and empirical grade distributions, an evaluation dimension often overlooked in prior work. Experiments compare single-task and multitask training, hard one-hot versus fuzzy and boundary-based soft labels, and rubric versus no-rubric conditions, with additional T5 and pairwise-pretrained variants. Results show that multitask BART with boundary-based soft labels and rubric context achieves lower mean absolute error and stronger grade-distribution alignment than single-task, hard-label, or code-only baselines. Fully fine-tuned T5 further improves distributional fidelity, while pairwise pretraining reduces numeric error at the cost of minority-class sensitivity. Collectively, the findings suggest that calibration-aware, rubric-guided training produces more instructor-like grading behavior than accuracy-optimized alternatives.
Adaptive programming practice often relies on fixed libraries of worked examples and practice problems, which require substantial authoring effort and may not correspond well to the logical errors and partial solutions students produce while writing code. As a result, students may receive learning content that does not directly address the concepts they are working to understand, while instructors must either invest additional effort in expanding content libraries or accept a coarse level of personalization. We present an approach for knowledge-component (KC) guided educational content generation using pattern-based KCs extracted from student code. Given a problem statement and student submissions, our pipeline extracts recurring structural KC patterns from students' code through AST-based analysis and uses them to condition a generative model. In this study, we apply this approach to worked example generation, and compare baseline and KC-conditioned outputs through expert evaluation. Results suggest that KC-conditioned generation improves topical focus and relevance to learners' underlying logical errors, providing evidence that KC-based steering of generative models can support personalized learning at scale.