MiniVer-V: Identifying Minimal Sufficient Evidence for Short Video Verification

Key points

• A core challenge in short-video fact-checking is identifying which evidence is sufficient to support a verification conclusion.1
• Existing approaches either give the verifier all available evidence, introducing noise, or select evidence by topical relevance, which conflates relatedness with sufficiency.1
• We identify evidential sufficiency as the selection criterion: whether a subset of evidence is adequate to support a confident verdict without redundancy.1
• We propose a two-layer verification framework that separates claim-video consistency, assessed from internal evidence, from factual verdict determination, which additionally requires external corroboration.1

Sources (1)

• [1]MiniVer-V: Identifying Minimal Sufficient Evidence for Short Video Verification
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 04:33 AM

  We introduce MiniVer-V, a benchmark of 195 short videos with three-way verdict annotations (supported, refuted, insufficient) and 5,510 multimodal evidence units spanning visual keyframes, speech transcripts, and web-retrieved external sources.

  A core challenge in short-video fact-checking is identifying which evidence is sufficient to support a verification conclusion.

Extractive summary: sentences quoted from the sources.