Reproducible AI Requires Reproducible Randomness

arXiv:2609.26461 · cs.AI · Submitted 2026-09-22 · Read on arXiv

cs.AI

Submitted: 2026-09-22

Updated: 2026-09-22

Code: https://github.com/DEShawResearch/random123

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Fidelity — 26× in this paper · explained in 2 episodes
• Mersenne Twister — 12× in this paper
• Monte Carlo — 11× in this paper
• Consistency — 9× in this paper · explained in 3 episodes
• Trace — 7× in this paper · explained in 2 episodes
• Verification — 6× in this paper · explained in 2 episodes
• High Performance Computing — 5× in this paper
• Accuracy — 3× in this paper · explained in 1 episode
• Adam — 3× in this paper · explained in 2 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Regularization — 3× in this paper · explained in 3 episodes
• Artificial Intelligence (AI) — 2× in this paper · explained in 2 episodes
• Clustering — 2× in this paper · explained in 2 episodes
• Computational overhead — 2× in this paper · explained in 2 episodes
• Core — 2× in this paper · explained in 2 episodes
• Modularity — 2× in this paper · explained in 9 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Data Augmentation — 1× in this paper · explained in 7 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• National Institute of Standards and Technology — 1× in this paper
• State Management — 1× in this paper · explained in 3 episodes
• University Clermont Auvergne — 1× in this paper

Sources

• The influence of the random numbers quality on the results in stochastic simulations and machine learning
• Torch.manual_seed(3407) is all you need: On the influence of random seeds in deep learning architectures for computer vision
• ASSESSING THE STOCHASTIC PROPERTIES OF MODERN PSEUDO-RANDOM GENERATORS FOR PARALLEL COMPUTING

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection