The content analyzes how AI, by processing fragmented information based on probability, can lose original attribution and context, leading to inaccurate responses. It suggests AI citation registries and repeatable record structures to reduce uncertainty and stabilize information provenance and recency.
The author started building Hyphae to create a cognitive substrate without large language models, but a simple baseline matched its performance, highlighting a critical issue. This project now focuses on ensuring provenance in AI-generated answers, which is essential for auditability in critical applications.
Schema markup alone is insufficient for reliable AI attribution due to inconsistencies, varied implementations, and the need for AI systems to interpret it, which introduces ambiguity. An AI Citation Registry is proposed as a machine-readable publishing system to reliably identify authoritative sources and ensure clear provenance and timestamps.
AI systems encounter attribution instability when interpreting fragmented government information across various vendor ecosystems, as authority signals are inferred rather than explicitly structured. This lack of explicit provenance hinders interoperability and unified responses for citizens.