Byzantine Accountability Without Consensus: Strong Eventual Consistency for Non-Associative, Stochastic, Robust Aggregation

arXiv:2607.10305 · cs.DC, cs.CR, cs.LG · Submitted 2026-07-11 · Read on arXiv

Ryan Gillespie

cs.DC, cs.CR, cs.LG

Submitted: 2026-07-11

Code: https://github.com/python/cpython

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

Terminology

• Consistency — 26× in this paper · explained in 3 episodes
• Aggregation — 21× in this paper · explained in 1 episode
• Robustness — 18× in this paper · explained in 5 episodes
• Ablation — 13× in this paper · explained in 1 episode
• Accountability — 10× in this paper · explained in 2 episodes
• Accuracy — 7× in this paper · explained in 1 episode
• Federated Learning — 7× in this paper · explained in 15 episodes
• Strong Eventual Consistency — 7× in this paper
• Verification — 7× in this paper · explained in 2 episodes
• Accountable Consensus-Free Aggregation — 2× in this paper
• Convergence Guarantees — 2× in this paper · explained in 3 episodes
• Decentralized Federated Learning — 2× in this paper · explained in 2 episodes
• International Conference on Machine Learning — 2× in this paper
• Model Merging — 2× in this paper · explained in 2 episodes
• Network and Distributed System Security Symposium — 2× in this paper
• Adversarial Attacks — 1× in this paper · explained in 1 episode
• Axioms — 1× in this paper · explained in 2 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Deferral — 1× in this paper · explained in 2 episodes
• Empirical Coverage — 1× in this paper · explained in 2 episodes
• Provenance — 1× in this paper · explained in 4 episodes
• State Management — 1× in this paper · explained in 3 episodes

Sources

• The Blocklace: A Byzantine-repelling and Universal Conflict-free Replicated Data Type
• A Composable CRDT Layer for Byzantine-Resilient Deterministic Reconstruction
• Decoupling Trust in Byzantine CRDTs: Fine-grained Post-Compromise Handling without Breaking Causality
• Casper the Friendly Finality Gadget
• DiLoCo: Distributed Low-Communication Training of Language Models
• Krum Federated Chain (KFC): Using blockchain to defend against adversarial attacks in Federated Learning
• Conflict-Free Replicated Data Types for Neural Network Model Merging: A Two-Layer Architecture Enabling CRDT-Compliant Model Merging Across 26 Strategies
• On Conflict-Free Replicated Data Types and Equivocation in Byzantine Setups
• Merkle-CRDTs: Merkle-DAGs meet CRDTs

Related papers

• iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems
• SAMM: Sharded Automated Market Maker
• InferScale: GPU-Native KV Injection for Personalized LLM Serving
• Vigil: Accountable Liveness against Selective Silence
• Steelhead: Interleaving Partially Synchronous and Asynchronous Commit Rules on a Shared DAG
• Pushing CPU Speech Synthesis to the Wall: Extreme Inference Tuning under Serverless Architecture and Billing