Publications
Code · Zenodo · October 7, 2026
ACE-LTT reproducibility package: Fail-Closed Certification of Multi-Stage AI Policies
Norkobil Saydirasulov Saydirasulovic, Young Im Cho, D.A. Davronbekov, Baxodir A. Nazarov, Abdinabi Mukhamadiyev
Abstract
Frozen code, preregistrations, registration and audit receipts, run records and archived detector and verifier outputs for the manuscript Fail-Closed Certification of Multi-Stage AI Policies (ACE-LTT). Source code is licensed under Apache-2.0; author-created non-code research artefacts are licensed under CC BY 4.0 where the authors hold the necessary rights (see LICENSE_SCOPE.md).
Safety Systems Engineering in AutonomyEthics and Social Impacts of AIFormal Methods in VerificationAI safetyreproducibility
More by Abdinabi Mukhamadiyev
- Expected query cost of Grover search under noise: code and dataZenodo · 2026
- Comparative Analysis of Methods for Improving the Classification Accuracy of Morphologically Similar Pollen Grain Classes on the CPD-1 DatasetSensors · 2026
- Exploiting Natural Information Redundancy for Reliability Control in Electronic Document Management: A Formal Framework and an Error-Annotated CorpusInformation · 2026
- Data and analysis code for: Foreign language anxiety and self-perceived progress among Uzbek students at a South Korean English-medium universityZenodo · 2026