Related papers: Unboxing Default Argument Breaking Changes in 1 + …

Agentic data science (ADS) pipelines have grown rapidly in both capability and adoption, with systems such as OpenAI Codex now able to directly analyze datasets and produce answers to statistical questions. However, these systems can reach…

With the move towards open research information, the DOI registration agency DataCite is increasingly used as a source for metadata describing research data, for example to perform scientometric analyses. However, there is a lack of…

Samples in large-scale datasets may be mislabeled due to various reasons, and Deep Neural Networks can easily over-fit to the noisy label data. To tackle this problem, the key point is to alleviate the harm of these noisy labels. Many…

One of the central tasks in software maintenance is being able to understand and develop code changes. Thus, given a natural language description of the desired new operation of a function, an agent (human or AI) might be asked to generate…

In most social choice settings, the participating agents express their preferences over the different alternatives in the form of linear orderings. While this clearly simplifies preference elicitation, it inevitably leads to poor…

In this work, we propose Answer-Set Programming (ASP) as a tool for rapid prototyping of dynamic programming algorithms based on tree decompositions. In fact, many such algorithms have been designed, but only a few of them found their way…

Open datasets play a crucial role in three research domains that intersect data science and education: learning analytics, educational data mining, and artificial intelligence in education. Researchers in these domains apply computational…

Software Analytics (SA) is a new branch of big data analytics that has recently emerged (2011). What distinguishes SA from direct software analysis is that it links data mined from many different software artifacts to obtain valuable…

While it is easy to automate coverage data collection, it is a time consuming/difficult/expensive manual process to analyze the data so that it can be acted upon. Complexity arises from numerous sources, of which untested or poorly tested…

Data attribution methods aim to quantify the influence of individual training samples on the prediction of artificial intelligence (AI) models. As training data plays an increasingly crucial role in the modern development of large-scale AI…

Neural models of code have shown impressive results when performing tasks such as predicting method names and identifying certain kinds of bugs. We show that these models are vulnerable to adversarial examples, and introduce a novel…

Detecting anomalies in energy consumption data is crucial for identifying energy waste, equipment malfunction, and overall, for ensuring efficient energy management. Machine learning, and specifically deep learning approaches, have been…

Acoustic scene classification (ASC) suffers from device-induced domain shift, especially when labels are limited. Prior work focuses on curriculum-based training schedules that structure data presentation by ordering or reweighting training…

From natural language processing to vision, Scaled Dot Product Attention (SDPA) is the backbone of most modern deep learning applications. Unfortunately, its memory and computational requirements can be prohibitive in low-resource settings.…

Here I present an investigation on the evolution and use of vocabulary in data science in the last 13 years. Based on a rigorous statistical analysis, a database with 12,787 documents containing the words "data science" in the title,…

Deep neural networks have demonstrated remarkable advancements in various fields using large, well-annotated datasets. However, real-world data often exhibit long-tailed distributions and label noise, significantly degrading generalization…

Autonomous data analysis agents are increasingly expected to conduct exploratory analysis with limited human guidance about data. However, existing benchmarks typically evaluate such agents in prior-guided settings, providing selected data…

Though exponentially growing health-related literature has been made available to a broad audience online, the language of scientific articles can be difficult for the general public to understand. Therefore, adapting this expert-level…

Computational notebooks, such as Jupyter notebooks, are interactive computing environments that are ubiquitous among data scientists to perform data wrangling and analytic tasks. To measure the performance of AI pair programmers that…

The alignment of large language models (LLMs) often assumes that using more clean data yields better outcomes, overlooking the match between model capacity and example difficulty. Challenging this, we propose a new principle: Preference…