17 papers
Constructing Executable Analytical Knowledge Representations for Meta-Analysis Synthesis Using an Agentic Harness
Lingbo Li, Anuradha Mathrani, Teo Susnjak
Meta-analysis synthesis highlights a fundamental challenge in knowledge-based scientific analysis: structured evidence does not by itself represent the analytical knowledge require…
A Reproducible Optimisation Protocol for Calibrating Prompt-Based Large Language Model Workflows in Evidence Synthesis
Teo Susnjak
This methods article presents a reproducible calibration workflow for prompt-based large language models (LLMs) in structured evidence-synthesis tasks. The method separates the rul…
Forecasting Commencing Enrolments Under Data Sparsity: A Zero-Shot Time Series Foundation Models Framework for Higher Education Planning
Jittarin Jetwiriyanon, Teo Susnjak, Surangika Ranathunga
Effective resource allocation in higher education depends on reliable enrolment forecasts, yet institutional planners frequently face data series disrupted by structural shifts. Th…
When Predictions Shape Reality: A Socio-Technical Synthesis of Performative Predictions in Machine Learning
Gal Fybish, Teo Susnjak
Machine learning models are increasingly used in high-stakes domains where their predictions can actively shape the environments in which they operate, a phenomenon known as perfor…
Stabilising Learner Trajectories: A Doubly Robust Evaluation of AI-Guided Student Support using Activity Theory
Teo Susnjak, Khalid Bakhshov, Anuradha Mathrani
While predictive models are increasingly common in higher education, causal evidence regarding the interventions they trigger remains rare. This study evaluates an AI-guided studen…
A Survey of Bugs in AI-Generated Code
Ruofan Gao, Amjed Tahir, Peng Liang +2
Developers are widely using AI code-generation models, aiming to increase productivity and efficiency. However, there are also quality concerns regarding the AI-generated code. The…