{
  "annotation_id": "859f0efd-2782-43d8-817d-4fdd5dc246b4",
  "date_created": "2026-02-17T05:53:23.747000Z",
  "date_modified": "2026-02-17T05:53:23.747000Z",
  "file_hash": "7c754f8060ec0461966fc08eed8575df33c1eb1e8244633515f1deecf56c82f6",
  "private": false,
  "record": {
    "abstract": "Time Series Foundation Models (TSFMs) have emerged as a promising approach for zero-shot financial forecasting, demonstrating strong transferability and data efficiency gains. However, their adoption in financial applications is hindered by fundamental limitations in uncertainty quantification: current approaches either rely on restrictive distributional assumptions, conflate different sources of uncertainty, or lack principled calibration mechanisms. While recent TSFMs employ sophisticated techniques such as mixture models, Student\u0027s t-distributions, or conformal prediction, they fail to address the core challenge of providing theoretically-grounded uncertainty decomposition. For the very first time, we present a novel transformer-based probabilistic framework, ProbFM (probabilistic foundation model), that leverages Deep Evidential Regression (DER) to provide principled uncertainty quantification with explicit epistemic-aleatoric decomposition. Unlike existing approaches that pre-specify distributional forms or require sampling-based inference, ProbFM learns optimal uncertainty representations through higher-order evidence learning while maintaining single-pass computational efficiency. To rigorously evaluate the core DER uncertainty quantification approach independent of architectural complexity, we conduct an extensive controlled comparison study using a consistent LSTM architecture across five probabilistic methods: DER, Gaussian NLL, Student\u0027s-t NLL, Quantile Loss, and Conformal Prediction. Evaluation on cryptocurrency return forecasting demonstrates that DER maintains competitive forecasting accuracy while providing explicit epistemic-aleatoric uncertainty decomposition. This work establishes both an extensible framework for principled uncertainty quantification in foundation models and empirical evidence for DER\u0027s effectiveness in financial applications.",
    "arxiv_id": "2601.10591",
    "authors": [
      "Arundeep Chinta",
      "Lucas Vinh Tran",
      "Jay Katukuri"
    ],
    "categories": [
      "cs.LG",
      "cs.AI",
      "q-fin.RM",
      "q-fin.TR"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "title": "ProbFM: Probabilistic Time Series Foundation Model with Uncertainty Decomposition",
    "url": "https://arxiv.org/abs/2601.10591",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "290ef4dd-58c1-45a3-9130-63d764f9e2bf",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}