Prospective evaluation of hearing aid fitting adjusted toward one-third functional gain in patients with sensorineural hearing loss.

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.

OcuTOP: a novel handheld corneal topography device with misalignment correction.

PURPOSE This study aimed to develop and validate OcuTOP, a novel handheld corneal topography device designed to overcome the limitations of conventional desktop systems. By incorporating software-based misalignment correction, OcuTOP seeks to provide accurate corneal curvature measurements without need for bulky mechanical alignment mechanisms. Validation was performed using a reference surface with known geometry to assess device accuracy and robustness. METHODS The OcuTOP device (75 g; 85 × 60 × 60 mm) was evaluated using a reference button with a known curvature (43.3 D). Controlled misalignments were introduced in longitudinal (Z: 42.5-43.5 mm), lateral (X: ±2 mm), and vertical (Y: ±2 mm) directions, generating 243 test cases. Images acquired by the device were analysed using neural network algorithms to estimate misalignment parameters, which were subsequently used to correct axial and tangential curvature maps and estimate button diameter, analogous to white-to-white corneal diameter. RESULTS OcuTOP demonstrated strong agreement with reference curvature values across all misalignment conditions (P for K1 & K2 = 0.365, 0.385 at Z = 42.5 mm; 0.606, 0.907 at Z = 43.0 mm; 0.297, 0.462 at Z = 43.5 mm). Even at maximum displacement (±2 mm in X and Y), central curvature predictions remained within 2% of true values, with mean astigmatism artifacts limited to <0.2 D at the apex of the surface. However, the errors in estimating curvature values increased progressively towards the periphery. Neural network estimation of Z distance achieved a mean error of 0.06 ± 0.05 mm, with no significant influence on the ability of the device to estimate curvature. WTW predictions were also consistent, with a mean value of 11.66 mm, differing by <1.5% from the reference diameter. CONCLUSIONS OcuTOP's software-based correction reliably compensates for translational and longitudinal misalignments, showing promising results for future studies enabling accurate corneal surface measurements without mechanical stabilisation.