CANote: Empowering Fact-checking Note Writing Through Scaffolded and Provenance-based Human-AI Collaboration

2026-06-05

AI Summary

This work addresses the excessive cognitive burden placed on ordinary users when crafting high-quality, evidence-based debunking notes in crowdsourced fact-checking. To mitigate this challenge, the authors propose CANote, an AI-assisted system that scaffolds human-AI collaboration through sub-claim decomposition, automated evidence retrieval, and structured co-drafting. The proposed workflow significantly enhances the quality of user-generated debunking notes—enabling non-experts to produce content comparable to that of experts—without increasing task duration or cognitive load, while also improving user satisfaction. Although users report a slight reduction in perceived control over the final content, the system effectively lowers the barrier to creating high-quality debunking notes, thereby democratizing participation in fact-checking efforts.

Abstract

Crowdsourced fact-checking mechanisms, such as X's Community Notes, play a critical role in mitigating the spread of misinformation. However, drafting high-quality, evidence-based debunking notes imposes a substantial burden on contributors. We present CANote, an AI-assisted debunking note writing system featuring evidence correlation and structured co-drafting. CANote scaffolds the workflow by extracting subclaims from social media posts, providing provenance through explicit links between subclaims and retrieved evidence, and generating neutral, structural drafts to support human reasoning. We evaluated CANote against manual writing (N=52 fact-checkers, N=52 lay users) on simulated X platform, where we found CANote significantly improves note quality. Notably, CANote enables lay users to write notes that have comparable quality to those written by experts. While the task completion time and perceived cognitive load remain comparable to manual drafting, CANote significantly increases user satisfaction. However, this assistance introduces a trade-off, resulting in a reduced sense of user ownership and control over the debunking note.

Problem

• fact-checking
• misinformation
• crowdsourcing
• debunking notes
• human-AI collaboration

Innovation

• scaffolded collaboration
• provenance-based evidence
• structured co-drafting
• fact-checking assistance
• human-AI collaboration