Welcome to Proofig. This guide provides an overview of the powerful detection capabilities of the Proofig system, ensuring the integrity of your scientific images by identifying various forms of image issues.

Overview of Capabilities

Proofig AI utilizes a vast database exclusively for detecting plagiarism, while also identifying duplications and manipulations within individual manuscripts. Let's look at the three main capabilities:

Detection of Reuse of Sub-Images From Published Manuscripts

Proofig detects the reuse of sub-images from different published manuscripts, commonly known as plagiarism. By utilizing PubMed's Source database, which contains more than 155 million images, Proofig can effectively identify instances of reused sub-images. This check also covers graphs, charts, diagrams, and plots against published literature.

Detection of Duplication or Reuse of Sub-Images

Proofig identifies duplication or reuse of sub-images within the same manuscript. This includes detecting instances of scaling, rotation, flipping, full and partial overlap, and other irregularities, ensuring that all images in your manuscript are unique and have not been reused improperly.

Detection covers graphs, charts, diagrams, and plots as well as microscopy images and blots.

Detection is per-manuscript. If you upload several manuscripts at once (up to 8), each is analyzed separately and manuscripts are not compared against each other.

Detection of Alterations or Manipulations

Proofig detects alterations or manipulations within a single sub-image. This includes identifying cloning, editing, deletion, and splicing, ensuring that each sub-image remains authentic and unaltered.

Detection of AI-Generated Microscopy Images. Identifies images created by the most widely used model, with continuous updates for new models.
​

Detection of Self-Plagiarism through Comparison with a Personalized Repository of
Prior Research. Prevents Reuse of a Researcher’s Own Previously Published Images.
​

My Database comparison also covers graphs, charts, diagrams, and plots.

Alongside the detection capabilities above, the Review Assistant explains each finding: what was found, what it means, its severity, the signal behind the finding, and recommended follow-up actions, tailored to your user type. A short "What do I see?" explanation is also shown inline within the report itself.

See Understanding Your Findings for more.

Here are just some examples of common image integrity challenges that Proofig can detect:
​
flipped images
​

cropped and rotated sections
​

FACS partial overlap
​

and spliced western blot images, demonstrating the system's capability to ensure the authenticity of your scientific data.

For Western blots, Proofig AI can also display a heatmap overlay highlighting the portion of the image suspected of manipulation.

To learn more about how Proofig can enhance the integrity of your research, explore our other tutorial videos and guides. For detailed instructions on using each feature, use the 'page tutorial' button in the upper right corner of each screen or visit our knowledge center. Thank you for using Proofig.