New Nexus-Score system aims to fix AI attribution gaps in scholarly research

A new paper on arXiv proposes Nexus-Score, a system designed to identify and address metadata gaps that hinder AI systems in accurately attributing scholarly work. Researchers found that missing metadata, such as author, institution, or funding links, prevents AI from correctly crediting research, often leading to fabricated citations or tool failures. The proposed Nexus-Score aims to act as a record-level check to guide repairs and prepare the scholarly record for increased AI-mediated use. AI

IMPACT Aims to improve AI's ability to correctly attribute scholarly work, potentially enhancing research integrity and discoverability.

RANK_REASON The item is a research paper published on arXiv detailing a new proposed system for addressing metadata gaps in scholarly attribution. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• Aadi Narayana Varma D
• alphaXiv
• arXiv
• CatalyzeX Code Finder for Papers
• Connected Papers
• CORE Recommender
• DagsHub
• Gotit.pub
• Hugging Face
• Litmaps
• Nexus-Score
• OpenAlex
• ScienceCast
• scite Smart Citations

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →