Part 11/13:
He invites feedback on whether this should be a free open-source project or a subscription-based service, stressing that such automation could save researchers months annually.
Ethical & Practical Considerations
While the technical achievement is impressive, Shapiro emphasizes responsible use:
The system relies on publicly available data; automated bulk downloads should respect arXiv's terms.
It does not scrape private or paid journals without permission.
Users should still critically assess AI-generated summaries and relevance.
He advocates for local, privacy-preserving processing rather than cloud-based crawling of entire repositories, ensuring respectful data use.