SPEAR Logo
0.3.0
  • 1. Overview
    • 1.1. Introduction
    • 1.2. Architecture
    • 1.3. Glossary
  • 2. Getting started
  • 3. Using SPEAR
  • 4. Request modes and evidence
  • 5. The confined execution path
  • 6. The model and its weights
  • 7. Operations and reference
  • 8. Contributing
SPEAR
  • 1. Overview

1. Overview

What SPEAR is, how its pieces fit together, and the vocabulary the rest of this documentation uses.

  • 1.1. Introduction
    • 1.1.1. What SPEAR is
    • 1.1.2. Four request classes
    • 1.1.3. The parts
    • 1.1.4. What SPEAR does
    • 1.1.5. Why the harness is the interesting part
    • 1.1.6. Layers of confinement
    • 1.1.7. Trust boundaries
    • 1.1.8. What this documentation covers
    • 1.1.9. Project
  • 1.2. Architecture
    • 1.2.1. Infrastructure overview
    • 1.2.2. Request classes and execution paths
    • 1.2.3. Runtime components
    • 1.2.4. Task ownership
    • 1.2.5. Context and memory
    • 1.2.6. Persistence ownership and retention
    • 1.2.7. Training data as a by-product
    • 1.2.8. Dependency direction
    • 1.2.9. Model capability boundary
    • 1.2.10. Default profile
    • 1.2.11. Provenance
  • 1.3. Glossary
Previous Next

© Copyright 2026, HEIG-VD/REDS. Last updated on 10 Oct 2026, 10:10.