National University of Computer and Emerging Sciences

Data and context matter: towards generalizing AI-based software vulnerability detection

AI-based solutions demonstrate remarkable results in identifying vulnerabilities in software, but research has consistently found that this performance does not generalize to unseen codebases. In this paper, we specifically investigate the impact of model architecture, parameter...

Numerical Assessment of Seismic Performance of a Lead-Rubber Base-Isolated RC Frame under Site-Specific Earthquake Excitations: A Case Study of Quetta, Pakistan

Quetta lies in one of Pakistan's most seismically active regions, where the Building Code of Pakistan (BCP-2007) assigns a design ground acceleration of 0.32 g and UBC-97 Seismic Zone 4 is adopted as the design basis. Despite this hazard, location-specific research on sei...

Eleven questions on Hantavirus cardiopulmonary syndrome management in the ICU

Hantavirus cardiopulmonary syndrome (HCPS) due to Andes virus (ANDV) is a fulminant yet potentially reversible cause of respiratory and circulatory failure requiring timely critical care. This article addresses eleven practical questions on ICU management, drawing on clinical exp...

Calibrated Station-Scale Temperature Downscaling from a Temperature-Agnostic Geospatial Foundation Model

We downscale coarse climate variables to station-scale temperature using frozen embeddings from a temperature-agnostic geospatial foundation model (Clay v1.5), and study when the resulting uncertainty can be trusted. Across three climate regimes, embedding-based decoders reduce R...

Annotation by Arithmetic: Exact Mark Placement on Construction Drawings by Separating Perception from Measurement

Automated construction estimation requires more than correct quantities: an estimator must be able to see, on the drawing itself, exactly which drawn element each line item refers to. Vision-language models identify millwork items on architectural sheets reliably, but the boundin...

SELM-CTR: a stacking ensemble deep learning model with SHAP-based analysis for large-scale click-through rate prediction

Purpose Click-through rate (CTR) prediction is a core challenge in digital advertising, as forecasting whether a user will click on an advertisement directly determines ad placement decisions and revenue outcomes. Standard machine learning and deep learning approaches achieve rea...