Related papers: Does chronology matter in JIT defect prediction? A…

As generative AI systems rapidly improve, a key question emerges: how do users adapt to these changes, and when does such adaptation matter for realizing performance gains? Drawing on theories of dynamic capabilities and IT complements, we…

Beyond training-time optimization, scaling test-time computation has emerged as a key paradigm to extend the reasoning capabilities of Large Language Models (LLMs). However, most existing methods adopt a rigid Planning-before-Trial (PbT)…

Although software managers are generally good at new project estimation, their experience of scheduling rework tends to be poor. Inconsistent or incorrect effort estimation can increase the risk that the completion time for a project will…

Data format innovations have been critical for machine learning (ML) scaling, which in turn fuels ground-breaking ML capabilities. However, even in the presence of low-precision formats, model weights are often stored in both high-precision…

Given the rapidly evolving nature of social media and people's views, word usage changes over time. Consequently, the performance of a classifier trained on old textual data can drop dramatically when tested on newer data. While research in…

Context: Application Programming Interface (API) code examples are an essential knowledge resource for learning APIs. However, a few user studies have explored how the structural characteristics of the source code in code examples impact…

The durability and quality of software contributions are critical factors in the long-term maintainability of a codebase. This paper introduces the Time to Modification (TTM) Theory, a novel approach for quantifying code quality by…

Scaling up language models has significantly increased their capabilities. But larger models are slower models, and so there is now an extensive body of work (e.g., speculative sampling or parallel decoding) that improves the (average case)…

Quasi-experimental methods have proliferated over the last two decades, as researchers develop causal inference tools for settings in which randomization is infeasible. Two popular such methods, difference-in-differences (DID) and…

We extend conformal inference to general settings that allow for time series data. Our proposal is developed as a randomization method and accounts for potential serial dependence by including block structures in the permutation scheme. As…

Conformal prediction methods enjoy strong theoretical and empirical predictive inference performance, provided the data is exchangeable, and predictors are trained in a memoryless fashion. However, these assumptions and constraints are…

Test-time training (TTT) enhances model performance by explicitly updating designated parameters prior to each prediction to adapt to the test data. While TTT has demonstrated considerable empirical success, its theoretical underpinnings…

Recent works have demonstrated the effectiveness of adapting pre-trained language models (LMs) for forecasting time series in the low-data regime. We build upon these findings by analyzing the effective transfer from language models to time…

The integration of Large Language Models (LLMs), such as ChatGPT and GitHub Copilot, into software engineering workflows has shown potential to enhance productivity, particularly in software testing. This paper investigates whether LLM…

It seems logical to assert that the dynamic nature of software engineering practice would mean that software effort estimation (SEE) modelling should take into account project start and completion dates. That is, we should build models for…

This article develops new closed-form variance expressions for power analyses for commonly used difference-in-differences (DID) and comparative interrupted time series (CITS) panel data estimators. The main contribution is to incorporate…

Time series forecasting holds significant importance across various industries, including finance, transportation, energy, healthcare, and climate. Despite the widespread use of linear networks due to their low computational cost and…

The recent developments of deep learning models that capture complex temporal patterns of crop phenology have greatly advanced crop classification from Satellite Image Time Series (SITS). However, when applied to target regions spatially…

Adaptive inference is a simple method for reducing inference costs. The method works by maintaining multiple classifiers of different capacities, and allocating resources to each test instance according to its difficulty. In this work, we…

Large Language Models (LLMs) have rapidly transformed software development, especially in code generation. However, their inconsistent performance, prone to hallucinations and quality issues, complicates program comprehension and hinders…