Community-based moderation offers a scalable alternative to centralized fact-checking, yet it faces significant structural challenges, and existing AI-based methods fail in "cold start" scenarios. To tackle these challenges, we introduce GitSearch (Gap-Informed Targeted Search), a framework that treats human-perceived quality gaps, such as missing context, etc., as first-class signals. GitSearch has a three-stage pipeline: identifying information deficits, executing real-time targeted web-retrieval to resolve them, and synthesizing platform-compliant notes. To facilitate evaluation, we present PolBench, a benchmark of 78,698 U.S. political tweets with their associated Community Notes. We find GitSearch achieves 99% coverage, almost doubling coverage over the state-of-the-art. GitSearch surpasses human-authored helpful notes with a 69% win rate and superior helpfulness scores (3.87 vs. 3.36), demonstrating retrieval effectiveness that balanced the trade-off between scale and quality.

翻译：基于社区的审核为集中式事实核查提供了可扩展的替代方案，但其面临显著的结构性挑战，且现有基于人工智能的方法在“冷启动”场景中表现不佳。为应对这些挑战，我们提出了GitSearch（缺口感知定向搜索）框架，该框架将人类感知的质量缺口（如缺失上下文等）视为首要信号。GitSearch采用三阶段流程：识别信息缺陷、执行实时定向网络检索以解决这些缺陷，以及合成符合平台规范的笔记。为便于评估，我们提出了PolBench基准，包含78,698条美国政治推文及其关联的社区笔记。我们发现GitSearch实现了99%的覆盖率，几乎是现有最佳方法的两倍。GitSearch以69%的胜率和更高的帮助性评分（3.87对3.36）超越了人工撰写的优质笔记，证明了其在规模与质量权衡中取得平衡的检索有效性。