JSTOR Digital Stewardship Services

• Text files:
• Text is extracted from PDFs if applicable.
• The extracted text, any images in the document, and specialized prompts are then sent to the LLM (GPT-4o) for processing.
• AI-generated metadata is presented for user review and refinement.
• Images:
  • Images are classified by type. If applicable, the tool identifies people in the image and identifies famous faces in a limited capacity.
  • The processed image data, along with specialized prompts, is sent to GPT-4o to generate metadata.
  • Users receive AI-generated descriptions, subjects, and keywords for verification and editing.

This approach ensures that AI serves as an assistive tool, not a replacement for expert judgment. Users retain full control, refining AI-generated suggestions to meet institutional and scholarly standards.

• AI provider data handling: OpenAI stores uploaded data for a maximum of 30 days to check for abuse or misuse before deleting it entirely. Your content is never used to train AI models.
• Data rights and deletion: You retain full rights to your uploaded content and generated metadata. If you delete your project, all associated data is permanently removed from JSTOR’s systems.
• Security and compliance: JSTOR maintains physical, technical, and administrative safeguards to prevent unauthorized access or malicious use. As a SOC2 compliant organization, our data security practices undergo annual independent third-party audits.
• Metadata storage and use: JSTOR stores generated metadata and user interactions to improve system performance.

• Handwritten and historical documents: The system is designed to effectively process handwritten documents and historical materials. While accuracy may vary depending on factors such as condition, language, legibility, and format, our technology is continuously improving to provide the best possible results.
• Non-English language materials: Our LLM service provider handles multiple languages by default, but optimization for specific non-English languages is still in progress.

• Text: PDFs (.pdf)
• Images: JPEG/JPG (.jpeg, .jpg)

Within these formats, the tool can generate metadata for a diverse range of content, including:

• Typed documents, handwritten letters, newspapers, books, and periodicals.
• Historical photographs, maps, posters, postcards, and advertisements.

We are exploring future expansions to support metadata generation for additional file types, such as audio and video, in the future.

• We honor our values first and foremost. JSTOR provides our community with credible content and tools to support scholarly research and learning. Our use of technology must enhance that credibility, not undermine it.
• We will listen closely and proceed cautiously. We recognize the concerns associated with AI and other emerging technologies, and are pursuing this work mindful of the very real considerations at hand. Our first step is to deepen our collective understanding through research and implementation in close collaboration with our community. We promise to use these tools safely.
• We empower people, and do not replace them. These tools should not be used to “do the work.” They should be designed to help people, especially students, deepen and expand their work.
• We will lead with care. We will deeply consider the aspirations and trepidations of the many communities we serve.

As we learn about and pursue this technology, we look forward to your engagement and insights to ensure we continue to deliver high-quality, trusted, impactful services that improve access to knowledge and education for people everywhere. Learn more about how we are exploring emerging technologies on the JSTOR platform.