the3y3-code/Algorithmic-Cowardice: Initial Research Release - Zenodo v1.0.0
Abstract
🚀 Initial Research Release (v1.0.0) This is the official release of the code and datasets for the research paper: "Algorithmic Cowardice: Cognitive Dissonance and Moral Conformity in Multi-Agent LLM Interactions" (DOI: 10.5281/zenodo.18902321). 📦 What's included: Core Framework: Asynchronous LangGraph orchestration for multi-agent "Moral Jailbreaking" simulations. Datasets: Complete raw results from the 1,500-run ablation study across three sampling temperatures (T=0.0, 0.3, 0.8). Evaluation Logic: Deterministic Pydantic-based scoring system for classifying AI ethical stances. This release serves as a permanent record for scientific reproducibility.
Fields of Study & Subjects
Ethics and Social Impacts of AI
Adversarial Robustness in Machine Learning
Ethics in Business and Education
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 7 March 2026
- Language
- EN