{
  "abstract": "Long gaps in time series are difficult to reconstruct reliably, and in power systems imputed load values inform dispatch and planning. Existing generative imputers are accurate but provide no finite-sample reliability guarantees under changing conditions. We introduce SPLICE (Self-supervised Predictive Latent Inpainting with Conformal Envelopes), which couples a JEPA encoder, a conditional latent bridge, an hourly-conditioned decoder, and Adaptive Conformal Inference (ACI). Controlled ablations indicate that long-horizon fidelity is driven more by the predictive representation than by generative complexity: under a matched bridge and decoder, JEPA outperforms reconstructive VAE and contrastive TS2Vec encoders, and once the representation is fixed a 5-step flow sampler matches or improves on a 50-step DDIM sampler at a 5-10x speedup. The same ordering is recovered on twelve hydrological catchments. Across thirteen load datasets at 91-day gaps, SPLICE attains the lowest mean Load-only MSE (0.056), winning 9 of 12 non-degenerate datasets against seven established baselines, and the best mean CRPS (0.182, 7.8% below the strongest competitor), while ACI holds 93-95% empirical coverage where static calibration under-covers by up to 7.5 percentage points. A pooled JEPA encoder transfers to four held-out datasets with only bridge and decoder adaptation.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2605.00126",
  "author_total": 1,
  "authors": [
    {
      "name": "Arnaud Zinflou"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/64cqje27xatb5.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2605.00126",
  "fulltext_url": null,
  "id": "64cqje27xatb5",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2605.00126",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "eess.SP"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "2208|Energy Load and Power Forecasting"
    ]
  ],
  "openalex": "W7160079269",
  "pdf_url": "https://arxiv.org/pdf/2605.00126",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-03",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/64cqje27xatb5.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:27:16Z",
      "native_id": "2605.00126",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2605.00126"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "SPLICE: Latent Diffusion over JEPA Embeddings for Conformal Time-Series Inpainting",
  "title_text": "SPLICE: Latent Diffusion over JEPA Embeddings for Conformal Time-Series Inpainting",
  "type": "preprint",
  "updated_at": "2026-10-30T12:27:16Z",
  "url": "https://research.draconitic.com/paper/64cqje27xatb5",
  "venue": "arXiv",
  "versions": []
}