Valori: A Deterministic Memory Substrate for AI Systems
This addresses the need for replayability and safe deployment in regulated sectors by preventing silent data divergence, though it is incremental as it builds on existing memory designs with a focus on determinism.
The paper tackles the problem of non-determinism in AI memory systems, which causes identical models and inputs to produce different memory states across hardware, and presents Valori, a deterministic memory substrate that ensures bit-identical states and results using fixed-point arithmetic and a state machine model.
Modern AI systems rely on vector embeddings stored and searched using floating-point arithmetic. While effective for approximate similarity search, this design introduces fundamental non-determinism: identical models, inputs, and code can produce different memory states and retrieval results across hardware architectures (e.g., x86 vs. ARM). This prevents replayability and safe deployment, leading to silent data divergence that prevents post-hoc verification and compromises audit trails in regulated sectors. We present Valori, a deterministic AI memory substrate that replaces floating-point memory operations with fixed-point arithmetic (Q16.16) and models memory as a replayable state machine. Valori guarantees bit-identical memory states, snapshots, and search results across platforms. We demonstrate that non-determinism arises before indexing or retrieval and show how Valori enforces determinism at the memory boundary. Our results suggest that deterministic memory is a necessary primitive for trustworthy AI systems. The reference implementation is open-source and available at https://github.com/varshith-Git/Valori-Kernel (archived at https://zenodo.org/records/18022660).