Oct 2026· Zenodo (CERN European Organization for Nuclear Research)
Abstract
This dataset contains the experimental materials for a study on whether publicly accessible conversational large language models (ChatGPT, Claude, Gemini and Microsoft Copilot) can generate road freight driver schedules that comply with EU driving-time and rest-period rules (Regulation (EC) No 561/2006 and Regulation (EU) No 165/2014). A single international freight transport scenario was tested at four levels of prompt structuring, from an open-ended instruction to a highly controlled prompt with explicit rules, fixed assumptions and a prescribed output format. The dataset includes: the shared transport scenario used in all experimental conditions; the exact system-level and user-level prompts for each of the four prompt levels; execution metadata for each test, including platform, model version and run details; the complete, unedited responses generated by the evaluated models (64 responses in total). The tests were run between February and June 2026 in private or history-disabled chat modes. The materials are provided to support transparency, independent verification and replication of the reported findings.
The results are packaged in the Greenfield Startup Model (GSM), which explains the priority of startups to release the product as quickly as possible, and the need to shorten time-to-market, by speeding up the development through low-precision engineering activities.
Carmine Giardino, Nicolò Paternoster, M. Unterkalmsteiner et al.· IEEE Transactions on Softwar...· 178 citations· ⚡14
Software startup companies develop innovative, software-intensive products within limited timeframes and with few resources, searching for sustainable and scalable business models.
M. Unterkalmsteiner, P. Abrahamsson, Xiaofeng Wang et al.· e-Informatica Software Engin...· 157 citations· ⚡17
This study conducts a case survey study based on the secondary data of the major pivots happened in 49 software startups, and demonstrates that customer need pivot is the most common among all pivot types.
Sohaib Shahid Bajwa, Xiaofeng Wang, Anh Nguyen-Duc et al.· Empirical Software Engineeri...· 127 citations· ⚡15
The comparison of adopter and non-adopter sample reveals three potential adoption inhibitor, security, data privacy, and portability, which underlines the importance of the technical and security perspectives for research investigating the adoption of technology.
Nattakarn Phaphoom, Xiaofeng Wang, S. Samuel et al.· Journal of Systems and Softw...· 111 citations· ⚡8
The ongoing work building a Raspberry Pi cluster consisting of 300 nodes is presented, with potential use cases being an inexpensive and green test bed for cloud computing research and a robust and mobile data center for operating in adverse environments.
P. Abrahamsson, S. Helmer, Nattakarn Phaphoom et al.· IEEE International Conferenc...· 110 citations· ⚡7
The findings show that speed related agile practices are used to a greater extent in comparison to quality practices, and that software startups who adopt the Lean Startup approach do not sacrifice quality for speed more than other startups do.
Jevgenija Pantiuchina, Marco Mondini, Dron Khanna et al.· International Conference on...· 84 citations· ⚡4
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Microsoft Research Blog· microsoft.comOct 15, 2026
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar appeared first on Microsoft Research.
