Science is built on trust. When that trust is broken, whether through honest errors or intentional misconduct, it impacts everyone.

This project is an open-access initiative dedicated to safeguarding scientific integrity. We build and maintain open-source tools that help detect manipulation, uncover paper mills, and ensure that the scientific record remains reliable.

From our perspective, scientific integrity is a continuum process acting toward cases of bad science in three very important directions: Prevention, Detection, and Correction.

• Prevention: Should include educating people on publication standards and avoiding mistakes or inappropriate behaviors.

• Detection: Should implement robust, transparent, and benchmarked systems capable of identifying inappropriate content and behaviors within and across publications.

• Correction: Should discuss policies that facilitate paper retraction and correction as soon as any error or misconduct is reported.

This project focuses on the Detection part by applying digital forensics techniques to the scientific integrity context.

We believe that tools meant to protect the truth should not be hidden behind closed doors.

All code in this organization is released under the GNU Affero General Public License (AGPL).

We chose AGPL to ensure that this project remains free and open forever. If you use our code to build a service, you must share your improvements back with the community.

We are currently working on ELIS, a dedicated system for scientific image analysis and robust forgery detection.

We are also currently hosting a challenge on Kaggle to detect and segment copy-move forgeries in biomedical images. Participate and learn more here: Recod.ai/LUC - Scientific Image Forgery Detection

We are building a community of developers, researchers, and forensic experts.

We are currently compiling an Awesome Research Integrity page to serve as a curated entry point for anyone who wants to collaborate. This resource will include a roadmap of needed tools, datasets for training models, and guides on digital forensics for beginners.

• Discuss: Have an idea or a question? Join the conversation on our Discussions Page.
• Contribute: Feel free to browse our repositories, open issues, or submit a PR.

If you share our desire for keeping science honest, you are very welcome here 🤗