2026-10-02T07:06:18Z https://dcpapers.dublincore.org/oai

oai:dcpapers.dublincore.org:952626928 2026-09-10 dcmi-2026 openaire

Empowering Researchers to Embody Open Science: An AI-Driven Framework for Librarian-Grade Metadata Generation Hayashi, Masaharu Asaoka, Makoto Kawai, Masashi Tanifuji, Mikiko To facilitate low-burden open science, we propose an AI-driven framework for institutional repositories. By integrating external APIs with large language models (LLMs) and vision-language models (VLMs), the system automatically generates metadata from DOIs or PDFs, including image-based summaries. This approach minimizes manual input while ensuring quality through provenance tracking, thereby streamlining the path to immediate open access. Dublin Core Metadata Initiative 2026-09-10 info:eu-repo/semantics/conferenceObject Text application/pdf text/html https://doi.org/10.23106/dcmi.952626928 https://dcpapers.dublincore.org/article/952626928 Dublin Core Metadata Initiative Conference Proceedings eng info:eu-repo/semantics/openAccess https://creativecommons.org/licenses/by/4.0/