Oct 2026· Zenodo (CERN European Organization for Nuclear Research)· 1 references
Abstract
Audited supplementary milestone, not completed five-engine certification. Four platform-configured engines passed two fresh-conversation captures each against a locally frozen twelve-case synthetic decision contract: 8/8 response captures and 96/96 recorded tuple declarations matched the canonical target. Original v1 negative results remain failed and are preserved at DOI 10.5281/zenodo.23286324. V2 explicitly fixes the step-string delimiter contract and adds confidence-boundary/no-match cases. The expanded instrument and changed capture route prevent attributing the result to wording alone. Luna and Opus also matched raw response content; GLM and Sol differed in formatting but matched canonical tuples. Attribution is by platform settings, not provider attestation; shared workspace/context remains accessible. Local freeze is not public preregistration. DeepSeek remains pending. Benchmark baseline: one local validator-only run completed 200/200 expected acceptance checks, with 100 valid accepted and 100 mutant rejected; mixed p50 0.0733 ms, p95 0.0878 ms. Short sandbox microbenchmark, not LLM or infrastructure throughput. Historical per-engine reported durations are descriptive n=2, not a vendor ranking. Forty offline regression checks passed. No stress tolerance, live healing, PQC validation or deployed enforcement claim is made. A future stress test is planned and not reported as complete. Dual Mesh Benchmark: NOT MEASURED. No comparative mesh, learning, recovery or resource-use result is claimed. AI assistance and capture provenance disclosed. All workload data is synthetic. Public evidence includes exact final outputs, instrument, frozen prompt, offline verifier and sanitized receipts. Raw API responses, private metadata, secrets, customer identity and PHI excluded. GitHub milestone and evidence. Research home: DCAI. DSOS Science. This software is a prototype and is provided for educational and research purposes only. It is not intended for production use, commercial deployment, or safety-critical environments. All systems are experimental and may contain defects on them.
This publication proposes a definition and a classification of agile software development approaches and analyses ten software development methods that can be characterized as being "agile" against the defined criterion.
P. Abrahamsson, O. Salo, Jussi Ronkainen et al.· arXiv.org· 727 citations· ⚡54
The study shows that agile practices improve both informal and formal communication, but indicates that, in larger development situations involving multiple external stakeholders, a mismatch of adequate communication mechanisms can sometimes even hinder the communication.
M. Pikkarainen, Jukka Haikara, O. Salo et al.· Empirical Software Engineeri...· 401 citations· ⚡48
The results indicate that software engineering work practices are chosen opportunistically, adapted and configured to provide value under the constrains imposed by the startup context.
Nicolò Paternoster, Carmine Giardino, M. Unterkalmsteiner et al.· Information and Software Tec...· 394 citations· ⚡54
The results show that the embedded industry has been able to apply agile methods in its development processes and that the appreciation of the agile methods and their individual practices appears to increase once adopted and applied in practice.
O. Salo, P. Abrahamsson· IET Software· 238 citations· ⚡9
Consequences of happiness and unhappiness that are beneficial and detrimental for developers' mental well-being, the software development process, and the produced artifacts are found.
D. Graziotin, Fabian Fagerholm, Xiaofeng Wang et al.· Journal of Systems and Softw...· 236 citations· ⚡13
The Mobile-D approach is briefly outlined here and the experiences gained from four case studies are discussed, which helped develop an agile development approach for mobile application development.
P. Abrahamsson, Antti Hanhineva, H. Hulkko et al.· Conference on Object-Oriente...· 225 citations· ⚡18
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.
MIT News · Artificial Intelligence· news.mit.eduOct 6, 2026
Writing as a participant and researcher, PhD student JS Tan SM ’22 has co-authored a new book about the rise of tech worker protests and the employer backlash that followed.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.