Category
642 papers
An open-source, human-verified workflow using large language models can accelerate electronic health record abstraction while improving accuracy and supports broader adoption of transparent artificial intelligence methods in clinical research.
This work introduces a static, decompiler-driven pipeline built on top of Ghidra that augments decompiled functions with binary-derived evidence including recovered stack regions, callgraph context, and p-code-derived features and presents the real-world evaluation as a diagnostic stress test rather than evidence of a deployable detector.
It is suggested that process-oriented metrics, particularly those related to code testing and development history, capture defect patterns more effectively per feature than static code structure metrics, offering practical guidance for software quality assurance.
The Heterogeneous Graph Feature Enhancer (HGFE) is proposed, an interface-preserving feature enhancement framework for downstream fault-localization models that consume feature matrices or feature vectors that consume feature matrices or feature vectors.
Reach audiences
Advertise in front of researchers, engineers, and readers.
Artic is proposed, an artifact-driven workflow compiler that transforms a natural-language workflow into an artifact-driven workflow in which each step declares the artifacts it reads and writes, constraints gate produced artifacts, and explicit control transfers route execution.
The results show that specification size alone does not predict implementation quality and that cross-agent transfer can produce substantial agent-dependent degradation, and suggest that specifications in heterogeneous SDD workflows should not automatically be treated as agent-neutral artifacts.
New approaches are proposed to simplify and formalize multi-panel figure composition, emphasizing rapid layout construction and experimentation while maintaining explicit control over publication parameters.
LLMs could serve as a quality control check during opioid policy surveillance research, supplementing human review, and benefit from best practices and technical guidelines for LLM utilization.
Drug use is an ancient practice, but its associated disorders represent a contemporary public health challenge. This study investigates the impact of proximal processes in childhood/adolescence and adulthood on substance use, focusing on the role of Therapeutic Communities (TCs). Using a qualitative methodology, 19 residents of TCs in the state of Rio de Janeiro were interviewed. Instruments included a screening test (ASSIST), a sociodemographic inventory, and semi-structured interviews. Content analysis of the interviews was supported by the Requalify.ai software, which proved to be an efficient tool for categorizing and visualizing qualitative data. Results indicate that factors such as dysfunctional family environments, violence, and early onset of consumption, often mediated by peer influence, are determining risk factors. On the other hand, peer social support within TCs emerges as a crucial protective factor, associated with positive changes reported by participants. The sample revealed an overrepresentation of Black and Brown individuals, highlighting the racial dimension in the history of drug use in Brazil. The study concludes that proximal relationships are decisive in both the etiology and recovery of substance use disorders, and that TCs, although controversial, can offer a supportive environment that favors change, especially through peer support and cohabitation.
The findings demonstrate that a software-based prototype integrating machine learning with image analysis can effectively simulate the core functions of a physical counterfeit-detecting banknote counter.
This study proposes a framework for identifying financial turbulence in construction project cash flows using the Relative Financial Reynolds Number (Re(t)). Inspired by fluid mechanics, the indicator captures transitions between stable, high-risk, and turbulent financial regimes and provides an early-warning mechanism for identifying liquidity stress in construction projects. Daily cash flow data from six residential construction projects in Izmir, Türkiye, were analyzed. The Relative Financial Reynolds Number was calculated as the ratio between cumulative cash flow and its daily rate of change, following an analogy derived from Bernoulli-type financial flow models. Financial regimes were classified using statistical boundaries based on the mean and standard deviation of Re(t). The empirical performance of the indicator was evaluated through ROC analysis, lead-time analysis, and Monte Carlo simulation. The results show that Re(t) captures financial turbulence periods more sensitively than conventional S-curves. ROC analysis yielded AUC values between 0.49 and 0.78 across projects, with a pooled AUC of 0.64, indicating moderate classification capability. Lead-time analysis suggests that turbulence signals appear approximately 2–3 weeks before liquidity stress events on average. Monte Carlo simulations further indicate a 60-day stress probability ranging between 0.75 and 0.90 across projects. The empirical analysis is limited to six projects within a single national context. Future research should test the model across different countries and project types and explore additional statistical validation techniques to strengthen the theoretical foundations of the approach. The six-project analysis demonstrates that Re(t), compared to conventional S-curves, more distinctly differentiates stable periods, risk clusters, and extreme turbulence regimes. It provided early indications of the impact of macroeconomic shocks (interest rate hikes, currency crises, political transitions) on project financing, while also capturing legal, parcel-based, and site-specific disruptions directly in the time series. As such, Re(t) functions as an effective early-warning mechanism for project managers, offering insights that cumulative S-curves alone cannot provide. These results strongly support the study’s main hypothesis that Re(t) serves as a more sensitive and responsive indicator of financial risks in construction projects. The primary contribution is the demonstration of the applicability of Re(t), derived from a hydraulic analogy, to project finance. This approach enables project managers to monitor not only cumulative progress but also daily volatilities and critical boundary exceedances. Thus, Re(t) can serve as a signal detection mechanism contributing to risk management.Secondly, project managers should integrate Re(t) into daily or weekly reporting to detect risks more quickly. Re(t) boundary exceedances should be carefully monitored, especially during interest rate shocks, currency crises, and liquidity shortages. Integration of the Re(t) algorithm into project finance software could facilitate practical applications. The study introduces an interdisciplinary analytical framework that connects fluid mechanics and construction finance. By conceptualizing cash flow dynamics through the Relative Financial Reynolds Number, the proposed method provides a practical early warning tool for monitoring financial turbulence in construction projects.
In his latest book, Professor Eugene Fitzgerald examines the forces that turn breakthroughs into value — and why innovation resists simple formulas.
MIT students designed, built, and tested a jet engine with AI copilots, assessing AI’s usefulness in developing high-performance aerospace systems.
Researchers developed an auditing technique to test generative AI models for malicious capabilities, without prompting them for illegal outputs.
A USAF cadet and a Lincoln Laboratory researcher found AI chatbots can help nontechnical service members produce viable software applications for their unique problems.
Our latest voice model has improved precision and lower latency to make voice interactions more fluid, natural and precise.
Education Innovation
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
