Replication Data for: Black Swan: Abductive and Defeasible Video Reasoning in Unpredictable Events
收藏DataCite Commons2026-03-13 更新2026-05-04 收录
下载链接:
https://researchdata.ntu.edu.sg/citation?persistentId=doi:10.21979/N9/HOAFUL
下载链接
链接失效反馈官方服务:
资源简介:
BlackSwanSuite is a benchmark for evaluating VLMs’ ability to reason about unexpected events through abductive and defeasible tasks. The tasks either artificially limit the amount of visual information provided to models while questioning them about hidden unexpected events, or provide new visual information that can change an existing hypothesis about the event. It contains over 3,800 MCQs, 4,900 generative, and 6,700 yes/no questions spanning 1,655 videos.
提供机构:
DR-NTU (Data)
创建时间:
2025-12-10



