发表机构
Utrecht University; Maastricht University; Radboud University（乌得勒支大学; 马斯特里赫特大学; 拉德堡德大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究介绍2026年ChildSafeAds共享任务，针对YouTube儿童向视频商业内容，含3360个视频，要求系统完成优惠类型识别等三项任务，还涉及数据标注与评估。
AI 中文摘要
ChildSafeAds是一项针对可能触达儿童和青少年的YouTube视频中商业内容的共享任务，包含来自939个频道的3360个视频。每个实例以提交至SponsorBlock的片段开头，SponsorBlock是一款开源众包浏览器扩展，其用户会标记赞助片段以便他人跳过。我们将该片段与其可用的文字记录、视频及频道信息，以及视频描述中链接的销售或服务页面配对。系统需完成三项任务：确定推广的优惠类型（任务1）、分配产品类别（任务2），以及识别法律风险标记（任务3）。证据被划分为四个累积访问级别，从文字记录到链接页面，以便可根据数据收集成本对结果进行比较。我们的数据中45.5%的视频未正确使用平台内广告披露方法（即“包含付费推广”标签）。GPT-5.4在专家组织者团队审查样本并迭代调整分类法、提示词和模型选择后生成标签；GPT-5.6-luna则独立对开发集进行标注。本报告描述了该任务、数据及评估情况，更新版本将加入参与系统和共享任务结果。
英文摘要
ChildSafeAds is a shared task on commercial content in YouTube videos likely to reach children and teenagers. The dataset contains 3,360 videos from 939 channels, each starting with a sponsor segment submitted to SponsorBlock. We pair each segment with its transcript, video, and channel information, plus a sales or service page linked from the video description. Systems determine the type of offer being promoted (ST1), assign product categories (ST2), and identify potential legal risks (ST3). Evidence is divided into four cumulative access levels, from the transcript to the linked page, so performance can be compared against the cost of collecting additional data. YouTube's "Includes paid promotion" label was absent from 45.5% of the videos. GPT-5.4 produced the labels after the organiser team, including a legal expert, reviewed samples and iterated on the taxonomy, prompts and model choices. GPT-5.6-luna independently labelled the development set to measure cross-model agreement. The evaluation received 21 entries; the highest mean macro-F1 was 0.735, while the best transcript-only entry reached 0.652. Across four system papers, the linked promotional page mainly helped identify what was being sold and added little to compliance-risk classification. The competition also exposed sensitivity to rare labels, advertiser overlap across splits and substantial variation in the ST3 labels.
