Metraipolis › archive › dc_bfa31676aed7
Selecting or Solving? What Best-of-N Verification Delivers in Video Reasoning — arXiv:2611.00507
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.00507
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:53:09.753Z
- SHA-256 of the archived text
27b8cb79e3a4be5159310af204fbf3504da5f4cbb3619f677750c5c7083a3ec3- Stable URL of this page
https://metraipolis.com/documento/dc_bfa31676aed7
How to cite
Selecting or Solving? What Best-of-N Verification Delivers in Video Reasoning — arXiv:2611.00507 — arXiv (en), https://arxiv.org/abs/2611.00507 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bfa31676aed7 (Metraipolis archive dc_bfa31676aed7, sha256 27b8cb79e3a4be5159310af204fbf3504da5f4cbb3619f677750c5c7083a3ec3)
BibTeX
@misc{dcbfa31676aed7,
title = {Selecting or Solving? What Best-of-N Verification Delivers in Video Reasoning — arXiv:2611.00507},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.00507},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bfa31676aed7; sha256 27b8cb79e3a4be5159310af204fbf3504da5f4cbb3619f677750c5c7083a3ec3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00507. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Answering a complex question about a long video is a grounding problem: the answer turns on a few seconds of evidence, and vision-language models remain well below human accuracy at finding them. The standard way to spend extra test-time compute on this kind of video reasoning is best-of-N selection: sample several chain-of-thought answers from a fixed model, then let a second model re-watch the video and pick one. Such pipelines are reported by a single headline number, their margin over a majority vote. That number conflates two effects with opposite deployment consequences: the benefit the second model adds by selecting among candidates, and the benefit it would have supplied by solving the question itself. We separate them, measuring the Selection Increment (SI) -- selection accuracy minus the same verifier's accuracy with the candidates withheld -- alongside the margin over self-consistency, across five long-video benchmarks. The Selection Increment is largest for the weakest verifiers: a verifier that solves poorly on its own leaves the candidates the most room to help. Beating the majority vote follows the opposite profile: where the vote already sits near its ceiling no verifier we test improves on it; below that ceiling only the strongest do. On Video-Holmes, the two come apart on a single pool of candidates -- a weak verifier gains +19.3 points from the candidates yet lands 7.1 points below the vote, while the frontier verifier gains the least and beats the vote. The weakest verifier also shows a failure mode: on EgoSchema it picks by where an option sits in the list rather than by what the video shows. Read as a merit score, SI puts a verifier that fails to beat a majority vote at the top of its ranking; read as an audit, it says which of the two effects a headline number delivers. Code is available at this https URL . Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2611.00507 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T18:16:52.882Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).