What Makes Software Issue Resolution Tasks Difficult for Agents?

Background. Advances in agentic systems are simultaneously, and rapidly, saturating benchmarks. Despite this often discussed phenomena, benchmark scores remain difficult to interpret due to the lack of control and characterization of task difficulty. More specifically, we currently have little understanding of what makes one task harder than another, and to what extent task difficulty is predictable from static task properties. Aims. We propose a measurement framework to investigate and systematically quantify what structural properties of software tasks correspond to agent success rates for issue resolution tasks. Method. We conducted a large scale empirical study on CoderForge-Preview, the largest open dataset of coding agent trajectories to date, by extracting features across task patch, repository and prompt. We evaluated the predictive power of each feature against task outcomes using ensemble methods, SHAP attribution, and effect size analysis. Results We found that task difficulty is substantially predictable from static features (AU C = 0.863) and is largely driven by patch fragmentation and repository scale. Prompt linguistic features become visible among top contributors for tasks in the mid-band, revealing a layered structure of difficulty. Conclusion. The difficulty of an issue resolution task is encoded in its structure. This enables static, pre-hoc difficulty estimation and lays the groundwork for difficulty-controlled benchmark construction for evaluation of agents.

A Preliminary Framework for Intersectionality in ML Pipelines

Machine learning (ML) has become a go-to solution for improving how we use, experience, and interact with technology (and the world around us). Unfortunately, studies have repeatedly shown that machine learning technologies may not provide adequate support for societal identities and experiences. Intersectionality is a sociological framework that provides a mechanism for explicitly considering complex social identities, focusing on social justice and power. While the framework of intersectionality can support the development of technologies that acknowledge and support all members of society, it has been adopted and adapted in ways that are not always true to its foundations, thereby weakening its potential for impact. To support the appropriate adoption and use of intersectionality for more equitable technological outcomes, we amplify the foundational intersectionality scholarship--Crenshaw, Combahee, and Collins (three C's), to create a socially relevant preliminary framework in developing machine-learning solutions. We use this framework to evaluate and report on the (mis)alignments of intersectionality application in machine learning literature.

Causality-Driven Neural Network Repair: Challenges and Opportunities

Deep Neural Networks (DNNs) often rely on statistical correlations rather than causal reasoning, limiting their robustness and interpretability. While testing methods can identify failures, effective debugging and repair remain challenging. This paper explores causal inference as an approach primarily for DNN repair, leveraging causal debugging, counterfactual analysis, and structural causal models (SCMs) to identify and correct failures. We discuss in what ways these techniques support fairness, adversarial robustness, and backdoor mitigation by providing targeted interventions. Finally, we discuss key challenges, including scalability, generalization, and computational efficiency, and outline future directions for integrating causality-driven interventions to enhance DNN reliability.

An Evaluation of LLMs for Detecting Harmful Computing Terms

Detecting harmful and non-inclusive terminology in technical contexts is critical for fostering inclusive environments in computing. This study explores the impact of model architecture on harmful language detection by evaluating a curated database of technical terms, each paired with specific use cases. We tested a range of encoder, decoder, and encoder-decoder language models, including BERT-base-uncased, RoBERTa large-mnli, Gemini Flash 1.5 and 2.0, GPT-4, Claude AI Sonnet 3.5, T5-large, and BART-large-mnli. Each model was presented with a standardized prompt to identify harmful and non-inclusive language across 64 terms. Results reveal that decoder models, particularly Gemini Flash 2.0 and Claude AI, excel in nuanced contextual analysis, while encoder models like BERT exhibit strong pattern recognition but struggle with classification certainty. We discuss the implications of these findings for improving automated detection tools and highlight model-specific strengths and limitations in fostering inclusive communication in technical domains.

Fairkit, Fairkit, on the Wall, Who's the Fairest of Them All? Supporting Data Scientists in Training Fair Models

Modern software relies heavily on data and machine learning, and affects decisions that shape our world. Unfortunately, recent studies have shown that because of biases in data, software systems frequently inject bias into their decisions, from producing better closed caption transcriptions of men's voices than of women's voices to overcharging people of color for financial loans. To address bias in machine learning, data scientists need tools that help them understand the trade-offs between model quality and fairness in their specific data domains. Toward that end, we present fairkit-learn, a toolkit for helping data scientists reason about and understand fairness. Fairkit-learn works with state-of-the-art machine learning tools and uses the same interfaces to ease adoption. It can evaluate thousands of models produced by multiple machine learning algorithms, hyperparameters, and data permutations, and compute and visualize a small Pareto-optimal set of models that describe the optimal trade-offs between fairness and quality. We evaluate fairkit-learn via a user study with 54 students, showing that students using fairkit-learn produce models that provide a better balance between fairness and quality than students using scikit-learn and IBM AI Fairness 360 toolkits. With fairkit-learn, users can select models that are up to 67% more fair and 10% more accurate than the models they are likely to train with scikit-learn.