PulseAugur
EN
LIVE 11:34:23
ENTITY SPARQL

SPARQL

PulseAugur coverage of SPARQL — every cluster mentioning SPARQL across labs, papers, and developer communities, ranked by signal.

Show in brief
Total · 30d
12
47 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
7
40 over 90d
TIER MIX · 90D
TOPICS
RELATIONSHIPS
SENTIMENT · 30D

7 day(s) with sentiment data

RECENT · PAGE 1/3 · 51 TOTAL
  1. COMMENTARY · CL_353533 ·

    AI agents need formal schemas, not just better prompts, for reliability

    This article argues that AI agents require formal ontologies and schemas, rather than just improved prompts, to ensure reliable operation in real-world business contexts. It highlights that while LLMs can reason well, t…

  2. RESEARCH · CL_351453 ·

    New KGQA methods tackle hidden paths and heritage data

    Researchers have developed two distinct approaches to improve knowledge graph question answering (KGQA) systems. One method, HeriKGQA, focuses on cultural heritage data by using large language models (LLMs) to interpret…

  3. TOOL · CL_340280 ·

    New VeriCypher framework improves LLM-generated Cypher queries for knowledge graphs

    Researchers have developed VeriCypher, a novel framework designed to improve the accuracy of Large Language Models (LLMs) in generating Cypher queries for knowledge graph question answering. This system addresses the ch…

  4. TOOL · CL_338592 ·

    OntoDoc framework automatically generates ontology descriptions

    Researchers have developed OntoDoc, a novel multi-agent framework designed to automatically generate natural language descriptions for ontology terms. This system addresses the common issue of ontology terms lacking acc…

  5. TOOL · CL_328219 ·

    ISWC2026 talk on AI-assisted data stories and Knowledge Graphs now online

    Slides from a presentation at ISWC2026 in Bari titled "From Queries to Narratives" are now available online. The talk focused on data stories that integrate text with live SPARQL queries to make Knowledge Graphs accessi…

  6. TOOL · CL_326878 ·

    GraphRAGProv enhances AI answer transparency with provenance tracking

    Researchers have introduced GraphRAGProv, a novel architecture designed to enhance the transparency and trustworthiness of answers generated by GraphRAG systems. This system leverages Resource Description Framework (RDF…

  7. RESEARCH · CL_323897 ·

    New ontology SFE-O standardizes AI knowledge for CO2 biomass extraction

    Researchers have developed SFE-O, a new ontology using the Web Ontology Language (OWL 2) to standardize knowledge representation for supercritical CO2 biomass extraction. This ontology organizes information across bioma…

  8. COMMENTARY · CL_320059 ·

    AI agent develops code, Mastodon discusses metadata versioning and Claude app

    An AI agent, Claude Code's Ultracode mode, was utilized for 12 hours to develop a SPARQL-in-SQLite Rust extension. While the generated code functions, it lacks reviewability. Separately, a discussion on Mastodon explore…

  9. TOOL · CL_304445 ·

    GraphRAG's token burn paradox: LLMs inflate costs, slow retrieval

    A new approach called GraphRAG aims to improve knowledge retrieval for LLMs by integrating vector search with knowledge graphs. However, a common implementation pitfall involves using LLMs for real-time graph traversal,…

  10. TOOL · CL_314117 ·

    Simon Willison uses Claude Code to build SPARQL extension for SQLite

    Simon Willison details an experiment using Claude Code's "Ultracode" mode to generate a SPARQL 1.1 implementation within SQLite, written in Rust. The process involved a lengthy generation period and subsequent refinemen…

  11. TOOL · CL_294896 ·

    SPARQL-LLM tops TEXT2SPARQL 2026 challenge with multilingual KGQA

    A new open-source system called SPARQL-LLM has achieved first place in the TEXT2SPARQL 2026 challenge, outperforming eight other approaches. This system excels at translating natural language questions into SPARQL queri…

  12. TOOL · CL_284575 ·

    New dataset trains AI agents to search Wikidata more effectively

    Researchers have introduced a new dataset and harness called Wikidata Search Traces, designed to train agents for querying large knowledge bases like Wikidata. The dataset addresses limitations in current language model…

  13. TOOL · CL_275008 ·

    New benchmark dataset aims to improve natural language to SPARQL querying for building automation

    Researchers have introduced Build2SPARQL, a large-scale benchmark dataset designed to improve the translation of natural language questions into SPARQL queries for building automation knowledge graphs. The dataset addre…

  14. TOOL · CL_273302 ·

    EU AI Act: New framework aids rights impact assessments for high-risk AI

    Researchers have developed a Semantic Web framework to aid in conducting Fundamental Rights Impact Assessments (FRIAs) for high-risk AI systems under the EU AI Act. This framework consolidates fragmented evidence from v…

  15. TOOL · CL_270365 ·

    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…

  16. TOOL · CL_269479 ·

    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…

  17. RESEARCH · CL_267359 ·

    CodeGraph knowledge graph unlocks source code semantics, aids LLM analysis

    Researchers have developed CodeGraph, a novel knowledge graph designed to semantically annotate source code from public repositories like GitHub. This system utilizes a code-specialized Large Language Model and a three-…

  18. TOOL · CL_254342 ·

    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…

  19. TOOL · CL_252027 ·

    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…

  20. TOOL · CL_249524 ·

    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…