RESTRICTED RESEARCH LICENSE

Version 1.0, 2026

Copyright (c) 2026 Markiian Matviiv, Ukrainian Catholic University
In partnership with the Ministry of Digital Transformation of Ukraine

1. PREAMBLE

These model weights ("Ukrainian LLM Guardrails") are machine learning 
artifacts trained on synthetic adversarial data for the protection of 
Ukrainian sovereign digital infrastructure. Given the sensitive nature of 
the underlying threat models and the potential for misuse, access is 
strictly controlled.

2. GRANT OF RIGHTS

Subject to compliance with all terms herein, the Licensor grants you a 
non-exclusive, non-transferable, royalty-free license to:

  a) Access and use the model weights solely for academic research, 
     defensive security research, or educational purposes;
  b) Run inference or fine-tune the models for safety classification 
     and content moderation tasks;
  c) Publish research findings that reference these models, provided 
     that the model weights themselves are not redistributed or made 
     publicly available.

3. RESTRICTIONS

You may NOT, without prior written approval from the Ministry of Digital 
Transformation of Ukraine:

  a) Use the models for any commercial, military, or intelligence 
     application;
  b) Redistribute, sublicense, sell, or otherwise transfer the model 
     weights or substantial portions thereof to third parties;
  c) Use the models to develop, improve, or benchmark offensive tools, 
     including but not limited to jailbreak generators, prompt injection 
     frameworks, or adversarial attack methodologies;
  d) Publicly disclose or publish model outputs, generated rationales, 
     or internal representations outside of aggregated statistical 
     analyses;
  e) Remove or obfuscate attribution to the Ministry of Digital 
     Transformation of Ukraine and Ukrainian Catholic University.

4. DUAL-USE AND ETHICAL OBLIGATIONS

These models classify adversarial content designed to test safety 
boundaries. By accessing them, you acknowledge that:

  a) The classification outputs are provided strictly for defensive 
     guardrailing and must not be used to bypass or undermine existing 
     safety systems;
  b) Any models derived from these weights should be deployed exclusively 
     for content moderation, guardrailing, or threat detection purposes;
  c) You will report any unintended harmful use or security 
     vulnerabilities discovered through this research to the Licensor 
     within 30 days.

5. ATTRIBUTION

Any publication, presentation, or derivative work based on these models 
must include the following citation:

  Matviiv, M. (2026). Efficient Guardrailing for the Ukrainian LLM 
  via Reasoning Distillation. Master's Thesis, Ukrainian Catholic 
  University. Models provided in partnership with the Ministry of 
  Digital Transformation of Ukraine.

6. TERMINATION

This license automatically terminates if you violate any of the terms 
herein. Upon termination, you must destroy all copies of the model 
weights and cease all use immediately.

7. DISCLAIMER

THE MODEL WEIGHTS ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, 
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF 
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, AND NONINFRINGEMENT. 
THE LICENSOR SHALL NOT BE LIABLE FOR ANY CLAIM, DAMAGES, OR OTHER 
LIABILITY ARISING FROM THE USE OF THE MODEL WEIGHTS.