- Updated: August 26, 2026
- 1 min read
Composable Trust Infrastructure for Manufacturing Knowledge Graphs: Cross-System Provenance, Temporal Reasoning, and Decision Traceability
Manufacturing knowledge graphs integrate data from heterogeneous industrial systems, yet they often suffer from a trust deficit. This article presents a composable trust infrastructure that combines four core capabilities—SHACL validation, PROV-O provenance, domain‑aware bi‑temporal versioning, and graph‑native decision objects—to deliver emergent trust properties such as full‑chain auditability and temporal decision traceability. The solution is built on a unified RDF architecture, leveraging shared correlation identifiers (entity URIs, ingestion activity IDs, and temporal keys) to enable compound queries across validation, provenance, temporal, and decision dimensions. An experimental ablation demonstrates that removing any single capability disables half of the composition queries, confirming the equal load‑bearing nature of each component. The infrastructure is validated on a testbed integrating eleven industrial sources (OPC UA, TIA Portal, eClass, AAS, ISA‑95, ISA‑18.2, SAP S/4HANA, Teamcenter, Opcenter EX, Insights Hub, SCM) under an 89‑class ISA‑95‑aligned ontology, resulting in a unified graph of 8,743 triples across five named graphs stitched by 81 owl:sameAs identity edges. Evaluation with realistic simulated data shows a full‑chain auditability query execution time of 31 ms. For more details, see the full paper on arXiv and explore related resources on our blog.
Andrii Bidochko
CTO UBOS
Andrii Bidochko is an AI entrepreneur and researcher focused on AI agents, reinforcement learning, and autonomous systems. He writes about the technologies shaping the future of machine intelligence, from frontier models and agent architectures to real-world AI applications.