Prevalence of non-union complication in femoral shaft fracture patients who underwent IM nailing surgery in Fatemi Hospital Ardabil.

Model-Based Agentic Software Engineering

MAGE explains how externalized knowledge, bounded action, independent evaluation, and retained human authority can compose into a governed engineering environment, and proposes tests of when that environment turns commodity intelligence into durable engineering progress.

Evaluating Inference-Time Defenses Against Package Hallucination in LLM-Generated Code

LLMs are increasingly used for code generation, yet they frequently hallucinate non-existent software packages, creating exploitable entry points into the software supply chain. We make four contributions to this problem. First, we show that prior evaluation methodologies systematically inflate hallucination rates by misclassifying standard-library modules as hallucinations in some languages. For Python, the overestimation reaches 9.4 percentage points. Second, we evaluate seven inference-time defenses for mitigating package hallucinations, including five guided decoding strategies (Greedy, Contrastive, DoLa, Nudging, and Active Layer-Contrastive Decoding), an iterative self-refinement approach (Self-Refine), and a Retrieval-Augmented Generation (RAG)-based defense.. Across eight models spanning five families and four programming languages (Python, JavaScript, Ruby, Rust), RAG reduces the package hallucination rate (PHR) in 18 of 32 model--language configurations. Third, we introduce Package Utility (PU) to assess whether defenses preserve valid and task-relevant recommendations. Among strategies evaluated, Greedy decoding provides the strongest average mitigation--utility trade-off. Fourth, we stress-test all strategies under adversarial prompts seeded with fabricated package names and find that PHR surges by up to 45 percentage points relative to standard prompts, with Ruby consistently the most vulnerable language (80.9--95.2\%). Under adversarial conditions, RAG and Self-Refine outperform all decoding-only strategies, indicating that robust defense requires either external grounding or iterative self-verification when prompts are actively hostile. Our results recast package hallucination as both a measurement problem and a decoding-time control problem, and they demonstrate that the choice of defense must be matched to the threat model and recommendation utility.

From design to verification: applying the software quality and test plans to the SST telescope control system for CTA

HawkEye: Web Vulnerability Analysis and Security Audit Tool

HawkEye is introduced, a modular, web-based vulnerability auditing platform designed to streamline security analysis by integrating multiple scanning tools within a unified dashboard and illustrates how consolidated reporting improves vulnerability prioritization for development teams.

Application for Tracking Bugs in Software Development: Improving Project Management Efficiency

By streamlining workflows and fostering collaboration, this platform offers a scalable, cost- effective solution for SMEs and contributes to software engineering by demonstrating how integrated technologies can modernize development processes in resource limited contexts, with potential for broader adoption in Albania and beyond.

GIS-based multi-criteria landslide susceptibility assessment in the Northwestern Himalaya, Jammu and Kashmir, India

This study presents a landslide susceptibility assessment using multiple parameters by integrating remote sensing, GIS, and field observations in the Jammu and Kashmir region. Eight contributing variables were selected for landslide susceptibility analysis: Land Use and Land Cover (LULC), proximity to roads, streams, slope gradient, slope orientation (aspect), geology, geomorphology, and elevation. In addition, an extensive landslide inventory consisting of 669 landslide events was developed using the Field Landslide Inventory Mapping (FLIM) application, LISS-IV satellite data, and field observations, covering an area of 42,950.43 km². Landslide susceptibility mapping (LSM) was carried out using the Analytical Hierarchy Process (AHP) approach and validated with MaxEnt software and field-generated landslide data. The resulting landslide susceptibility map was classified into five categories: very high, high, medium, low, and very low susceptibility zones. Based on the AHP approach, these zones cover 3.65% (1,569.0483 km²), 24.43% (10,492.8912 km²), 51.56% (22,147.2369 km²), 18.81% (8,079.2199 km²), and 1.54% (662.0301 km²) of the study area, respectively. The weighted overlay and MaxEnt models proved effective for landslide vulnerability mapping, with MaxEnt achieving AUC values of 0.82 for training data and 0.807 for testing data, indicating good predictive performance. Field validation further showed that 87% of landslides occurred within high and very high susceptibility zones. The Jackknife test identified road proximity, slope, and stream proximity as the most significant independent variables influencing landslide occurrence. The generated landslide susceptibility map provides important insights for reducing landslide risk and serves as a valuable tool for infrastructure planning, community development, and disaster management in the region.