SOURCE-LINKED INTELLIGENCE
TwinPast: Benchmarking Historical Evidence Use in Streaming Video Understanding with Evidence Contrastive Video Pairs
High accuracy on streaming video benchmarks does not establish whether a model uses visual history. Our review of OVO-Bench and StreamingBench finds that recent frames suffice for 32% of sampled historical questions, while models also answer many questions correctly from the question and options alone. We introduce TwinPast to test whether answers correctly follow changes in history, using 350 human-reviewed video pairs spanning five historical tasks. Each pair holds the recent video context, question, and ordered options fixed while changing critical historical evidence and the correct answer
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-10-30T16:31:23.000Z
First collected: 2026-11-02T10:21:21.339Z. This is not the publication date.