Abstract We measure cross-boundary collaboration in an open-source software (OSS) ecosystem by reconstructing the bipartite contributor–repository graph of 464 cybersecurity-focused projects and $11{,}372$ 11 , 372 contributor identities active over October 2001–May 2022, seeded from the curated Rawsec Cybersecurity In...
Lucia Gomez Tejeiro, thibaut chataing, Julian Jang-Jaccard et al.· EPJ Data Science· 0 citations
Replication package for "Selection information is not free: a preregistered study of small-language-modeldeployment decisions" (submitted to Information and Software Technology). The study asks whether charging deployment-selection policies for the information they buy changes which policylooks best. In ten environment...
Hwang Seongyeon· Zenodo (CERN European Organi...· 0 citations
Vibe coding has made a profound change in software creation visible: humans can increasingly express what they want in natural language while artificial intelligence systems generate, modify, test, and repair the code that realizes that intention. This paper argues that the deeper transition is not simply from manual c...
Rogério Figurelli· Zenodo (CERN European Organi...· 0 citations
Malva Malva is an artifact for studying tool-mediated interaction failures in agentic GUI software. It contains a defect library built from 40 open-source applications, a task suite for reproducing representative failures, and MalvaGuard, a static checker that detects missing tool-interaction guards before agent execut...
Anonymous Author(s)· Figshare· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Abstract. We develop and evaluate a method for learning solution operators to nonlinear problems governed by partial differential equations (PDEs). The approach is based on a finite element discretization and aims at representing the solution operator by a multilayer perceptron that takes problem data variables as inpu...
Mats G. Larson, Carl Lundholm, Anna Sofie Persson· SIAM Journal on Scientific C...· 1 citation
Abstract Large Language Models (LLMs) have shown high capabilities in several software development-related tasks such as program repair, documentation, code refactoring, debugging, and testing. However, training these models requires massive amount of data and significant computational resources. Adapters are specializ...
Meghdad Dehghan, Jie JW Wu, Fatemeh H. Fard et al.· Empirical Software Engineeri...· 1 citation
A machine learning (ML) model using two preprocedural cardiac CT-derived metrics, automatically extractable with open-source tools, predicts 1-year mortality after TAVI.
D. Vignale, Andrea Corvaglia, A. Palmisano et al.· Radiology Advances· 0 citations
The concept of comprehension debt is extended: the deferred learning and maintenance cost that arises when AI-assisted production outpaces a learner's or team's ability to explain, test, modify, and justify the resulting software.
Overview This release accelerates simulation of (especially) few-qubit Quregs, adds control and performance tuning utilities for MPI and GPU superusers, adds randomised Trotter simulation, and reduces the likelihood of QuEST symbols colliding with other software stacks. Optimisations QuEST's simulation of few-qubit Qur...
Tyson Jones, aniabrown, Jacob Wilkins et al.· Zenodo (CERN European Organi...· 0 citations
Objectives (1) To conduct a meta-analysis on the structure of the TPB extended model to examine the predictive effects of its components on physical activity participation among adolescents and college students; (2) To investigate the moderating effects of key research dimensions, including participant groups, cultural...
Yao Yin, Xiao-Dong Sun, Jing-Wang-Xiao-E-Deng-Yu He et al.· Frontiers in Public Health· 0 citations
Research software and numerical source data accompanying the study "Vibroacoustic spectral-contrast encoding of sound direction in passive objects revealed by single-point laser Doppler vibrometry". Version 0.1.0 is a numerical and statistical reproduction package for seven figures. Computation begins at supplied per-t...
Jia-Wei Chen, Yi-Hao Jiang, Yu-Chuan Lee et al.· Zenodo (CERN European Organi...· 0 citations
We describe the document-reading model behind Money Maxer, an agent finance team that closes a simulated month for a mid-market software company. The system's premise is that no agent is trusted: every journal entry is re-performed by a small deterministic kernel before it can post. Inside that design we ask how small,...
Evaluating Microsoft Copilot at enterprise scale requires test data that captures the full complexity of real organizations, yet real enterprise data contains sensitive information that cannot be used for evaluation under any circumstances. The post From synthetic enterprise data evaluations to real Microsoft Copilot AI confidence appeared first on Microsoft Research.
Microsoft Research Blog· microsoft.comOct 29, 2026
Host Sowbhagya Suresh shares some of the latest news and cutting-edge research from across Microsoft—from understanding the challenges facing coding agents to uncovering how people use AI at work and improving extended-range weather forecasting. The post Microsoft Research Focus – Edition #97 appeared first on Microsoft Research.
“X-Hinges” helps design and 3D print items like lamps and gloves with an interactive twist: automatically embedded sensors that perceive and adaptively respond to human contact.
StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across subjects like chess, writing, and mathematics. The post Simulating student learning for better AI tutoring appeared first on Microsoft Research.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
