Metraipolis › archive › dc_01736ad12e18
Limits of Confidence in Diffusion — arXiv:2609.20581
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.20581
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T03:22:14.234Z
- SHA-256 of the archived text
cdd9d82301824ed2f8792cb0d944ea98d3f14dcacc0601120d604d98ceaea71e- Stable URL of this page
https://metraipolis.com/documento/dc_01736ad12e18
How to cite
Limits of Confidence in Diffusion — arXiv:2609.20581 — arXiv (en), https://arxiv.org/abs/2609.20581 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_01736ad12e18 (Metraipolis archive dc_01736ad12e18, sha256 cdd9d82301824ed2f8792cb0d944ea98d3f14dcacc0601120d604d98ceaea71e)
BibTeX
@misc{dc01736ad12e18,
title = {Limits of Confidence in Diffusion — arXiv:2609.20581},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.20581},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_01736ad12e18; sha256 cdd9d82301824ed2f8792cb0d944ea98d3f14dcacc0601120d604d98ceaea71e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20581. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Discrete diffusion, including remasking and uniform-state samplers, generate a sequence by writing multiple token positions per step, drawing each from a per-position distribution and choosing which positions to write from those same distributions. For domains of general interest (pixels, phonemes, or words) there are inherent dependencies between tokens. We show that a step matches the training distribution only when the positions it writes are conditionally independent given the tokens already fixed, that no product of per-position distributions can match a dependent group, and that per-position distributions do not determine whether a group is dependent: two joint distributions can have identical per-position marginals while differing in which combinations of values occur. On ScanAndAdd, a synthetic task whose joint distribution is available in closed form, we verify that every group of two or more undetermined positions a confidence ranking writes is dependent, and measure the generated distribution to be $29\times$ the sampling-noise floor total variation while per-sample metrics are $1.0$. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.20581 — 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 2026-10-10T03:04:13.753Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).