Metraipolis › archive › dc_9c8d55fa6a32
From Truncation to Commitment: Persistent Context in Uniform Discrete Diffusion — arXiv:2609.01043
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.01043
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T06:33:53.328Z
- SHA-256 of the archived text
bfc20a3784306a43e7be24e5fd13542a5e19fe04c8f24a6502e4f45a87f9445d- Stable URL of this page
https://metraipolis.com/documento/dc_9c8d55fa6a32
How to cite
From Truncation to Commitment: Persistent Context in Uniform Discrete Diffusion — arXiv:2609.01043 — arXiv (en), https://arxiv.org/abs/2609.01043 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9c8d55fa6a32 (Metraipolis archive dc_9c8d55fa6a32, sha256 bfc20a3784306a43e7be24e5fd13542a5e19fe04c8f24a6502e4f45a87f9445d)
BibTeX
@misc{dc9c8d55fa6a32,
title = {From Truncation to Commitment: Persistent Context in Uniform Discrete Diffusion — arXiv:2609.01043},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.01043},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9c8d55fa6a32; sha256 bfc20a3784306a43e7be24e5fd13542a5e19fe04c8f24a6502e4f45a87f9445d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01043. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Uniform-state discrete diffusion models update all tokens in parallel while keeping every position revisable. Even when the commonly used top-$p$ rule leaves only one candidate at a position, that choice affects only the current reverse step and can be revised at the next sampling step. We ask what changes when selected hypotheses instead become persistent context for later predictions. We therefore propose committed reveal sampling (CRS), a training-free sampler that stores selected argmax tokens and inserts them into subsequent model inputs. Our analysis gives a rationale for selecting later and for keeping selected tokens visible. Under the exact forward process, the Bayes error of selecting a clean token cannot increase as noise decreases, while in a simple latent-mode model, keeping the selected token visible helps later parallel predictions agree on the same sequence-level choice. Empirically, paired experiments on Duo-distilled then separate this persistent effect from single-step top-$p$ restriction and scalar temperature scaling. Under the same finalization rule, CRS without top-$p$ truncation reaches lower generative perplexity (GenPPL) than fixed $p=0.95$ and $p=0.9$ baselines across budgets of 8--64 function evaluations (NFE). At 64 NFE, the comparison at matched unigram entropy also gives lower GenPPL for CRS, yielding a more favorable GenPPL--entropy tradeoff. Base Duo shows the same direction in a descriptive comparison, while other diversity and continuation metrics can rank these operating points differently. These results identify support restriction and persistent context as distinct controls of that tradeoff. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Probability (math.PR); Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2609.01043 — 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 2026-10-17T06:15:12.853Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).