---
title: "Towards Reducing Researchers’ Burden in Open Science: An AI-Driven Framework for Automated Metadata Entry"
authors:
  - name: "Masaharu Hayashi"
    affiliation: "National Institute of Informatics"
    orcid: "https://orcid.org/0000-0002-1451-9300"
  - name: "Makoto Asaoka"
    affiliation: "National Institute of Informatics"
    orcid: "https://orcid.org/0000-0002-5307-5183"
  - name: "Masashi Kawai"
    affiliation: "National Institute of Informatics"
    orcid: "https://orcid.org/0009-0001-0720-4474"
  - name: "Mikiko Tanifuji"
    affiliation: "National Institute of Informatics"
    orcid: "https://orcid.org/0000-0001-5284-6364"
doi: "10.23106/dcmi.952626928"
article_id: "952626928"
url: "https://dcpapers.dublincore.org/article/952626928"
pdf: "https://dcpapers-data.dublincore.org/articles/dcmi-2026/952626928/files/dcmi-952626928.pdf"
section: "Posters"
conference: "International Conference on Dublin Core and Metadata Applications 2026"
published: "2026-08-01"
license: "CC-BY-4.0"
version_of_record: false
publication_stage: "proof"
citable_as_version_of_record: false
---

# Towards Reducing Researchers’ Burden in Open Science: An AI-Driven Framework for Automated Metadata Entry

Masaharu Hayashi, Makoto Asaoka, Masashi Kawai, Mikiko Tanifuji

> **Uncorrected proof — not the Version of Record.**
> This text is circulating for author and editor correction and may still change.
> Do not cite it as the version of record; check the article URL above for the final text.

## Abstract

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.

## 1 Background

The global shift toward open science requires researchers to make publicly funded results openly accessible[1].
In Japan, the publication of academic papers and evidence data resulting from public funding has become mandatory.
As reliance on Article Processing Charges (APCs) for open access becomes financially unsustainable, open access with institutional repositories is increasingly vital.
To implement open science in practice, self-archiving must be streamlined through technical solutions[2].
This study presents a proof of concept (PoC) for an AI-driven framework that simplifies repository registration while maintaining high metadata quality.

## 2 Methods

The framework automates metadata entry for academic papers and evidence data using a DOI or a PDF (Figure 1).
For academic papers, it prioritizes metadata from external APIs, using an LLM as a fallback for PDF extraction.
For evidence data, basic metadata are inherited from the academic paper metadata, while summaries are generated from images and captions.
A VLM describes visual elements, which are integrated into a coherent summary by an LLM.
To ensure integrity, the LLM evaluates generated fields for consistency[3] prior to researcher review.
The framework maintains provenance by recording whether each field was AI-generated, corrected, or verified.
Additionally, the framework uses the Open Policy Finder to provide information about the version of the paper that researchers can deposit in an institutional repository, and exports metadata using the JPCOAR schema.

![A pipeline architecture diagram. A user at a UI feeds into an Orchestrator API that runs six sequential stages: Fetch or Upload PDF; Extract Full-text with Image and Table; Extract Metadata and OA policy via API (Use LLM for fallback); Generate Image/table metadata using LLM/VLM; Human Review and Correction; and Output Formatted Metadata. Two sub-processes branch from the orchestrator: Extract Metadata using External API (Unpaywall, OpenAlex, Crossref, Open Policy Finder) and Generate Metadata using LLM/VLM (Generate and Formatted Metadata using LLM/VLM, Faithfulness Assessment).](https://dcpapers-data.dublincore.org/articles/dcmi-2026/952626928/content/figures/fig-1-poc-architecture.png)

*Figure 1. PoC Architecture for Repository Deposit using AI.*

## 3 Results

This framework automates metadata generation from DOIs or PDFs, transforming deposits into a simple verification task.
Testing on 100 papers yielded high F1 scores: 0.989 (DOI), 0.860 (title), and 0.803 (creator).
The system leverages a complementary approach where APIs provide canonical data and the LLM extracts verbatim strings (e.g., ROR identifiers and keywords) from PDFs.
This allows researchers to focus on low-confidence, AI-flagged entries.
Additionally, by extracting data-level metadata from images and tables, the framework significantly minimizes the manual effort required for separate dataset registration.

## 4 Conclusion

This study demonstrates a low-burden repository workflow by integrating external APIs with LLM/VLM-based generation.
While automated quality control requires further refinement, this PoC confirms AI's potential to mitigate administrative overhead.
Future work will focus on optimizing human–AI collaboration to achieve a fully streamlined and sustainable scholarly communication environment.

## References

1. U.S. Office of Science and Technology Policy. *Ensuring Free, Immediate, and Equitable Access to Federally Funded Research*. OSTP Memorandum, 2022.
2. L. Rothfritz, L. Matthias, H. Pampel, and M. Wrzesinski. *Current challenges and future directions for institutional repositories: A systematic literature review*. J. Assoc. Inf. Sci. Technol., vol. 77, 2026. [doi:10.1002/asi.70016](https://doi.org/10.1002/asi.70016).
3. Y. Liu, D. Iter, Y. Xu, S. Wang, R. Xu, and C. Zhu. *G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment*. Proc. EMNLP, 2023. [doi:10.18653/v1/2023.emnlp-main.153](https://doi.org/10.18653/v1/2023.emnlp-main.153).