Crowdsourced fact-checking systems have been adopted by major social media companies such as X, Meta, TikTok and Google with the aim of combating misleading information at scale without relying on centralized editorial control. These systems have been developed around a common underlying concept: a bridging mechanism that identifies notes flagging misleading information when they receive support from people with different perspectives rather than simple majority support.
arXiv:2606. 30905v1 Announce Type: cross Abstract: Community Notes, a bridging-based crowd-sourced fact-checking system, has emerged as a new mechanism for moderating misleading information on social media and has been adopted by major platforms including X, Facebook, Instagram, Threads, and TikTok.
By Soham De, Isaac Slaughter, Jiawei Guo, Qiao-Yun Cheng, Jiayuan Yan, Sruti Banerjee, Martin Saveski
The paper investigates why misinformation spreads more quickly on engagement‑based platforms by dissecting the recommendation algorithm of X. It identifies an engagement fungibility mechanism that rewards instant reactions (likes, retweets) over thoughtful engagement (replies, quotes), allowing misinformation—which tends to attract instant reactions—to receive more recommendations. The authors validate this mechanism through a simulation on the USC X 2024 election corpus, showing that adjusting metric weights has little effect, while requiring thoughtful engagement before amplification can significantly reduce the credibility exposure gap without harming mainstream content or engagement.
By Pan Li, Shuang Gao
arXiv:2606. 18268v1 Announce Type: cross Abstract: Community-based fact-checking that relies on cross-consensus is expanding rapidly on social media platforms.
By Changxi Wen, Shuning Zhang, Bohao Chu, Yuwei Chuai, Hui Wang, Dai Shi, Xin Yi, Hewu Li
Social media fact-checking has long been challenged by evidence-level and aggregation-level conflicts, where erroneous evidence mimics authoritative news sources. To capture this challenge and support...
arXiv:2609.00508v1 Announce Type: new
Abstract: Social media fact-checking has long been challenged by evidence-level and aggregation-level conflicts, where erroneous evidence mimics authoritative ne...
By Shuning Zhang, Dai Shi, Bohao Chu, Hui Wang, Yuwei Chuai, Yifan Wang, Jingruo Chen, Simin Li, Xin Yi, Hewu Li
arXiv:2607. 01251v1 Announce Type: cross Abstract: Debate, where AI agents argue opposing positions, has emerged as a key approach to scalable oversight.
By Yuyang Jiang, Chacha Chen, Teng Wu, Liwen Sun, Han Liu, Shi Feng, Chenhao Tan
The article describes the design, operation, and impact of the Community-Driven API and AI Writer for Openly Scaling Community Notes on X. It explains how the AI Note Writer API, launched in September 2025, allows AI to propose notes while users retain control over which notes are shown, and highlights that the Community Writer—an open‑source client—generates 52% of notes deemed helpful and is faster than other writers. The study shows AI notes complement human contributions, covering 42% of posts with helpful notes that have no human alternative, and 30% of posts with only human notes, indicating a synergistic relationship.
"whyItMatters":"The work demonstrates how an open, community‑driven AI API can scale content moderation and enrichment on a social platform while preserving user control and complementing human effort."
By Brad Miller, Jay Baxter, Jiansong Chao, Keith Coleman, Sophie Hilgard, Daniel Ortiz
The paper introduces the Active Provenance Gate (APG), a post‑debate verification layer for multi‑agent debate synthesis that audits debate logs, applies self‑correction, and blocks unsupported claims before publication. Empirical studies show that APG more than doubles provenance fidelity in crisis simulations and that users prefer explicit failure reports over fabricated consensus. The work shifts data origin tracing from passive logging to active conditional blocking, addressing safety gaps in large‑language‑model‑based debate systems.
By Jakub Mas{\l}owski, Jaros{\l}aw A. Chudziak
arXiv:2606. 10159v1 Announce Type: cross Abstract: AI is increasingly used to support scientific peer review, from manuscript screening, reviewer assistance to editorial triage.
By Lin Li, Qi Zhang, Xander Davies, Jianing Qiu, Yarin Gal
arXiv:2608. 07762v1 Announce Type: new Abstract: LLM benchmarks can build an organization's reputation and attract customers, but only when results are transparent and verifiable.
By Sahil Pardasani, Madhusudan Singh
MiniRep is a reputation‑based aggregation system designed for multi‑agent debate (MAD) that remains robust even when malicious agents are present. It evaluates agents on both their current task performance and historical reputation, while preventing groups of agents with highly similar responses from dominating the final decision. Experiments on the MATH benchmark show that MiniRep consistently outperforms conventional MAD aggregation and other reputation‑based approaches across a wide range of attack scenarios.
By Jiaming Zhang, Yuwan Liu, Yue Huang, Sisi Duan