Metraipolis › archive › dc_1c5cc158bbec
Have I Seen Enough? Frozen Video-Language Models Encode Evidence Readiness — arXiv:2610.08560
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.08560
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:23:49.511Z
- SHA-256 of the archived text
e4d17cd511529e5703cdce73339d57db704504d9366b63963b6a3f274b18977e- Stable URL of this page
https://metraipolis.com/documento/dc_1c5cc158bbec
How to cite
Have I Seen Enough? Frozen Video-Language Models Encode Evidence Readiness — arXiv:2610.08560 — arXiv (en), https://arxiv.org/abs/2610.08560 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1c5cc158bbec (Metraipolis archive dc_1c5cc158bbec, sha256 e4d17cd511529e5703cdce73339d57db704504d9366b63963b6a3f274b18977e)
BibTeX
@misc{dc1c5cc158bbec,
title = {Have I Seen Enough? Frozen Video-Language Models Encode Evidence Readiness — arXiv:2610.08560},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.08560},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1c5cc158bbec; sha256 e4d17cd511529e5703cdce73339d57db704504d9366b63963b6a3f274b18977e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08560. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Streaming video-language models must decide not only what to answer, but whether the evidence needed for the current question has arrived. Existing systems learn that decision as a separate trigger; we ask whether an unmodified model already computes it. We show that frozen VideoLLMs carry a linearly readable evidence-readiness signal, labelled from timestamped evidence rather than from model output. It decodes in all seven models of a shared byte-identical evaluation (AUROC 0.733-0.905 under the strictest not-ready sampling, where a fitted clock is near chance), and a probe fitted without any of a benchmark family's footage still reads that family. It is question-conditioned: on byte-identical windows, changing only the question reverses the readout on 66.1% of pairs, while every question-blind control is at chance by construction. The model can answer incorrectly and still encode readiness: AUROC remains 0.722 among wrong answers. Readiness also beats uncertainty estimators and their supervised combination on latency-matched answer selection, and tracks independent human judgments more closely than confidence. Released streaming triggers are also linear readouts, yet a trained trigger read on its own base model's activations is approximately orthogonal to readiness and decodes it far less accurately than a probe. We turn the readout into Readiness Gating, an answer-timing policy that improves accuracy by up to +9.75 pp at matched video duration with negligible computational overhead. How much it gains varies with the accuracy headroom the task makes available: across 26 configurations the gain tracks that headroom, and an intervention that moves it over identical pixels moves the gain with it. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Computation and Language (cs.CL); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.08560 — 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 2026-10-07T11:15:39.501Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).