Tag
This paper introduces a neuro-symbolic meta-policy for temporal knowledge-graph memory in partially observable reinforcement learning, combining RDF-based graph representations with symbolic memory management heuristics to achieve inspectable and adaptive control.
ProbSPARQL is an upward-compatible SPARQL extension that models uncertain numeric values as random variables with probabilistic RDF literal datatypes, enabling distribution-aware queries, probabilistic filters, and divergence-based joins. Implemented on Apache Jena ARQ, it addresses challenges in querying multi-dimensional uncertain measurement data from circular manufacturing knowledge graphs.
Microsoft has open-sourced Ontology Playground, a static web app for learning, designing, and exporting ontologies compatible with Microsoft Fabric IQ, featuring a visual editor, RDF/XML support, and an interactive graph.