Engineering Standards / Artificial Intelligence
Mixture of Experts (MoE) & State Space Model (SSM/Mamba) Architecture Standard
Defines architecture and evaluation for mixture-of-experts and state-space models, including routing, sparsity, memory, throughput, scaling, and deployment tradeoffs.
Publication record
MYTHOS-AI-0011
- Publication class
- Standard
- Status
- Candidate
- Pages
- 32
- Review or expiration
- Dec 16, 2026
- File size
- 204 KB
Reader
Read the publication
Searchable, bookmarked PDF, 32 pages. Loads on request (204 KB).
Candidate status describes publication review state. It does not establish certification, legal compliance, implementation conformance, benchmark reproduction, or product readiness.
Related
More in Artificial Intelligence
MYTHOS-AI-0001 Agentic Framework Benchmark and Evaluation Standard
Defines a reproducible benchmark for agent frameworks, including orchestration, memory, tools, safety boundaries, observability, durability, interoperability, and evidence-backed evaluation.
MYTHOS-AI-0002 Model Intelligence, Training, and Deployment Standard
Defines model selection, training, evaluation, packaging, deployment, inference, governance, and lifecycle requirements for production AI systems.
MYTHOS-AI-0003 Applied Natural Language & LLM Evaluation Standard
Defines evaluation of language-model quality, grounding, reasoning, retrieval, hallucination resistance, multilingual behavior, and task-specific natural-language performance.
MYTHOS-AI-0004 AI Software Engineer & Code Generation Benchmark Standard
Defines benchmarks for AI-assisted software engineering, including code generation, repository reasoning, testing, repair, security, and autonomous engineering workflows.
MYTHOS-AI-0005 Applied Automation & Infrastructure-as-Code Benchmark Standard
Defines evaluation of AI systems performing infrastructure automation and infrastructure-as-code tasks, emphasizing correctness, safety, rollback, policy, and reproducibility.
MYTHOS-AI-0006 AI Alignment, Red-Team, & Sycophancy Evaluation Standard
Defines alignment and adversarial evaluation for AI systems, including red-team methodology, instruction hierarchy, sycophancy, deception, unsafe autonomy, and behavioral assurance.