{
  "abstract": "Score-based diffusion methods usually perturb data with Brownian Gaussian noise, corresponding to a light-tailed forward stochastic differential equation (SDE). For market time series this SDE can be a poor abstraction: limit order book (LOB) order flow is heavy-tailed, bursty, and occasionally jump-like. We study STOCHLOB, a training-only score-matching framework that changes the forward diffusion corruption law while leaving the deployed predictor deterministic. Instead of Brownian-only Gaussian corruption, the noising process uses two non-Gaussian SDE-inspired alternatives: jump-Lévy noise through a compound-Poisson variance mixture, and clipped $α$-stable noise through a positive-stable Gaussian scale mixture. These corruptions inject finite jumps and heavy-tailed residuals into training without requiring reverse-time diffusion sampling at inference. The resulting score target has a useful interpretation: its radial factor $h_t(r)$ is the posterior expected corruption precision, so large residuals are weighted according to the latent corruption scale that most plausibly generated them. On chronologically held-out Coinbase LOB data, the proposed variants remain competitive on uncorrupted BTC and altcoin test horizons and improve several realized tail-window stress diagnostics. An exploratory Feishu A-share transfer study further tests whether the probability outputs remain usable under transaction costs and trading-rule constraints. Code and configuration files are available at https://github.com/ArshiAbolghasemi/Penny.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.21081",
  "author_total": 10,
  "authors": [
    {
      "name": "Arshia Abolghasemi"
    },
    {
      "name": "Seyed Reza Tavakoli"
    },
    {
      "name": "Parsa Naderi"
    },
    {
      "name": "Nazanin Mirzaei"
    },
    {
      "name": "Behrad Jahani"
    },
    {
      "name": "Saba Yousefzadeh"
    },
    {
      "name": "Tahereh Javaheri"
    },
    {
      "name": "Mohammad Hosein Rohban"
    },
    {
      "name": "Gholamali Aminian"
    },
    {
      "name": "Ali Habibnia"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/dmfwjmf8f09ng.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.21081",
  "fulltext_url": null,
  "id": "dmfwjmf8f09ng",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.21081",
  "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.LG"
    ],
    [
      "arxiv",
      "q-fin.TR"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1803|Stock Market Forecasting Methods"
    ]
  ],
  "openalex": "W7222852315",
  "pdf_url": "https://arxiv.org/pdf/2610.21081",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-24",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/dmfwjmf8f09ng.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:35:49Z",
      "native_id": "2610.21081",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.21081"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "StochLOB: Heavy-Tailed Score Matching for Robust Limit Order Book Trend Prediction",
  "title_text": "StochLOB: Heavy-Tailed Score Matching for Robust Limit Order Book Trend Prediction",
  "type": "preprint",
  "updated_at": "2026-10-30T12:35:49Z",
  "url": "https://research.draconitic.com/paper/dmfwjmf8f09ng",
  "venue": "arXiv",
  "versions": []
}