{
  "id": 10,
  "url": "https://arxiv.org/abs/2607.11459v1",
  "title": "A Multimodal Dataset for Large Language Model Applications in the Energy Domain",
  "summary": "This paper presents the mAIEnergy dataset, an open-access, multimodal corpus developed to support Large Language Model (LLM) applications in the energy sector. The dataset integrates approximately 50,000 textual documents, 20,000 images, 25 million numerical time series records, and 2 million geospatial and relational data entries. It includes policy and regulatory texts, scientific articles and news articles, satellite and contextual imagery, electricity system measurements, weather observation",
  "authors": "Costas Mylonas, Magda Foti",
  "category": "research",
  "topics": "regulation,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-13T12:08:43.000Z",
  "fetched_at": "2026-07-14T14:14:15.663Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/10",
  "original_url": "https://arxiv.org/abs/2607.11459v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}