It presents a universal post-processing approach to boost AKE methods. Our experiments on 17 benchmark datasets showed significant improvements across 5 AKE methods.

Thanks all the co-authors (@jasonnurse.bsky.social,Yang Xu,Jie Guo, @hooklee.bsky.social) for their effort and collaboration.

🎉 Starting a new chapter at Istanbul University-Cerrahpaşa!

Delighted to join the Department of Computer Engineering as an academic. Looking forward to contributing to research and teaching in this vibrant academic community.

🛠️ Example applications enabled by the dataset:

• Detailed stats for 39 orgs + ~2k authors (activity span, avg. word counts, % unique claims)
• Predicted political bias scores (via a pre-trained model)
• Credibility assessment based on historical signals

✅ ~118k English fact-checking reports from 39 organisations:

✔️ All are active signatories of @factchecknet.bsky.social and/or EFCSN
🗓️ Spanning 1995–2025
💬 Includes 7k+ claims investigated by multiple organisations

Nowadays, it is quite simple to generate deepfakes for specific purposes. For example, the image below was generated with thispersondoesnotexist.com and is totally fake! Such images are commonly used in fake profiles to convince other users of the profiles' authenticity.

While my starter pack is growing with new members, it is (and will be) certainly incomplete. So, I suggest checking out other similar starter packs by searching on blueskydirectory.com (Thanks @mubashariqbal.com for this amazing service).

As an example, those including "Misinformation" are below 👇