{
  "abstract": "Next-latent prediction fits a map from the current embedding to the next one. LeNEPA carries this objective to time series, replacing the stop-gradient of next-embedding prediction with the isotropy penalty of LeJEPA. A world model is a transition kernel that can be rolled out. The one-step regression identifies a conditional mean, and a mean is a kernel only in special cases. For a linear-Gaussian Markov latent, the mean transition and the innovation covariance are fixed by the one-step problem, and the open-loop squared error at horizon $K$ equals the trace of the sum of the pushed-forward innovation covariances. That error grows with $K$ after the one-step fit is exact. If the conditional mean is nonlinear, composing it is not the multi-step conditional mean. If the observation is a non-injective function of a Markov state, a memoryless one-step map does not determine future observations, while a short window can. An isotropy penalty is a function of the embedding marginal, so its partial derivative in the transition weights is zero. On a scalar autoregression with coefficient $0.9$, the one-step mean squared error is $0.998$ and the $16$-step open-loop error is $5.10$. On a hidden rotation, an eight-step window reaches $16$-step error $0.056$, while the current scalar alone reaches $0.778$. Raising the isotropy weight from $0.1$ to $10$ leaves eight-step latent error inside $[0.78,0.85]$ on three seeds.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.36227",
  "author_total": 3,
  "authors": [
    {
      "name": "Shitong Wang"
    },
    {
      "name": "Zhongang Cai"
    },
    {
      "name": "Yuzhou Hong"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/e7ssbgbnryvnp.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.36227",
  "fulltext_url": null,
  "id": "e7ssbgbnryvnp",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.36227",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.CV"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1711|Time Series Analysis and Forecasting"
    ]
  ],
  "openalex": "W7214932873",
  "pdf_url": "https://arxiv.org/pdf/2609.36227",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-28",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/e7ssbgbnryvnp.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:25:41Z",
      "native_id": "2609.36227",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.36227"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "One-Step Next-Latent Prediction Is Not a World Model",
  "title_text": "One-Step Next-Latent Prediction Is Not a World Model",
  "type": "preprint",
  "updated_at": "2026-10-30T12:25:41Z",
  "url": "https://research.draconitic.com/paper/e7ssbgbnryvnp",
  "venue": "arXiv",
  "versions": []
}