The System That Evolves: A Three-Layer Taxonomy for Persistence, Consolidation, and Test-Time Adaptation, with Honest Measurements at Small Scale
Abstract
A three-layer taxonomy for how an LLM system changes over time, each layer tied to a falsifiable containment property: Persist (external memory, no weight change - reversible), Consolidate (offline gated LoRA weight updates - gated-and-revertible), and Adapt (test-time training during inference - sandboxed-and-discarded). We implement all three on a ~10.5M-parameter checkpoint and measure them honestly at small scale. Persistence: 15/18 facts answered warm with zero model weights touched (AST-verified) and 0 fabrication cold. Consolidation: the pre-registered
Fields of Study & Subjects
Security and Verification in Computing
Advanced Data Storage Technologies
Parallel Computing and Optimization Techniques
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 15 July 2026
- Language
- EN
- Document type
- Preprint