SPARQL
PulseAugur coverage of SPARQL — every cluster mentioning SPARQL across labs, papers, and developer communities, ranked by signal.
- used by ScienceCast 70%
- used by alphaXiv 70%
- used by Gotit.pub 70%
- uses alphaXiv 70%
- uses ScienceCast 70%
- used by CatalyzeX 70%
- used by Resource Description Framework 70%
- used by Wikidata 70%
- used by Web Ontology Language 70%
- used by SHACL 70%
- used by Ontology Web Language 70%
- used by Knowledge Graph Question Answering 70%
7 day(s) with sentiment data
-
New benchmark evaluates LLMs for geospatiotemporal power outage analysis
Researchers have introduced GeoOutageBench, a new benchmark designed to evaluate Large Language Models (LLMs) in their ability to perform geospatiotemporal Knowledge Graph Question Answering (KGQA) for analyzing power o…
-
AI framework enhances legal reasoning with explainability for law enforcement
A new framework is proposed for decision support systems in law enforcement, focusing on explainability and compliance with regulations like the EU's General Data Protection Regulation (GDPR) and the Law Enforcement Dir…
-
New system uses controlled semantics for LLM knowledge graph queries
Researchers have developed a system called NLKGQ that leverages controlled semantics within an LLM's context window for natural language knowledge graph query execution. This framework uses a formal OWL ontology to tran…
-
Reinforcement learning boosts zero-shot Text-to-SPARQL generation
Researchers have explored the use of reinforcement learning for zero-shot Text-to-SPARQL generation, a task crucial for knowledge graph question answering. They applied Group-Relative Policy Optimization (GRPO) to the Q…
-
New 'data stories' method simplifies cultural heritage knowledge graph access
Researchers have developed a novel approach called "data stories" to make cultural heritage knowledge graphs more accessible for exploration and quality assessment. These narratives combine explanatory text, images, and…
-
LLM knowledge graph QA: Answer path crucial, syntax irrelevant
Researchers have investigated the impact of different components within a graph retrieval-augmented generation pipeline for large language models (LLMs) performing question answering over knowledge graphs. Their finding…
-
Beyond Vector Search: Semantic Graphs for Zero-Hallucination AI
This article argues for a shift from probabilistic AI methods like vector stores and RAG to deterministic semantic querying using knowledge graphs, SPARQL, and RDF. It highlights the limitations of vector stores in hand…
-
New frameworks enhance knowledge graph question answering with LLMs and agentic navigation
Researchers have developed two novel frameworks for question answering over knowledge graphs (KGs). The first, KGFR, uses a collaborative approach between a large language model (LLM) and a structured retriever (KGFR) t…
-
New framework automates federated SPARQL query generation for knowledge graphs
Researchers have developed RENSA, a framework designed to automate the generation of federated SPARQL queries for knowledge graphs. This system enhances existing metadata standards by incorporating class and authority i…
-
New AI tool detects temporal disinformation in political news
Researchers have developed a Temporal Coherence Score (TCS) to identify temporal inconsistencies in political news, a form of disinformation that bypasses traditional fake news detectors. The TCS system uses a four-stag…
-
New ontology standardizes distributed AI workflows across edge, fog, and cloud
Researchers have developed a new SAREF-compliant ontology designed to standardize the representation of distributed AI workflows across edge, fog, and cloud environments. This ontology extends the SAREF4SYST framework t…
-
New framework improves LLM-based knowledge graph question answering
Researchers have introduced a new framework called Constrained Entity Selection under Partial Knowledge (CES-PK) for knowledge graph question answering (KGQA) using large language models (LLMs). This method focuses on v…
-
GrOIL pipeline automates formal ontology creation using LLMs
Researchers have developed GrOIL, a novel seven-stage pipeline for automatically constructing formal ontologies from domain documents. This system ensures corpus grounding, vocabulary consistency, and expressivity, prod…
-
New framework integrates RDF with Differential Dynamic Logic for AI systems
Researchers have developed RDFdL, a novel framework that combines Resource Description Framework (RDF) with Differential Dynamic Logic (dL). This integration aims to bridge the gap in representing and reasoning about bo…
-
New platform enables machine learning on visual web page representations
Researchers have developed a new platform to enable machine learning applications on web pages by capturing their visual and structural properties. This platform uses the FitLayout tool to render web pages, storing thei…
-
AutoSchema framework enables AI agents to query diverse knowledge graphs without training
Researchers have developed AutoSchema, a novel framework designed to enable language model agents to query heterogeneous knowledge graphs without prior training. This system addresses the challenge of varying schemas, i…
-
New semantic graph framework integrates wheat production data
Researchers have developed a novel semantic graph framework called the Sustainable Wheat Production Datahub to integrate diverse datasets related to wheat cultivation. This framework utilizes the Knowledge Acquisition a…
-
Open Ontologies: Rust MCP Server for AI-Native Ontology Engineering
The Tesseract Academy has released Open Ontologies, a Rust-based MCP server designed for AI agents to engineer production-grade OWL ontologies. This toolchain offers significant performance improvements over traditional…
-
New methodology validates semantic mappings using metaphysical ontology commitments
Researchers have developed a new methodology for validating semantic mappings between disparate data sources. This approach is grounded in the metaphysical commitments of the ontologies themselves, offering a novel fram…
-
New benchmark ENTLORE tests latent organizational reasoning in enterprise QA · 6 sources tracked
Researchers have introduced ENTLORE, a new benchmark designed to evaluate latent organizational reasoning in enterprise question answering systems. This framework reconstructs enterprise structures from documents and or…