{
  "abstract": "Generative lossy compression combines a rate-limited representation with a stochastic decoder that preserves source-dependent information while generating unresolved detail. We ask what remains reusable when a rate-distortion-perception (RDP) system selected for one operating point is transferred to a prescribed conditional-generation task. We distinguish the single-letter RDP factorization from its block-code implementation and compare Full Redesign with three increasingly restrictive transfer strategies. Renderer-Only Transfer retains only the renderer and redesigns semantic steering. Representation-Induced Transfer additionally retains the semantic latent law induced by the original representation. Full-Model Transfer retains a compatible RDP code, marginalizing over the task conditional law to form its semantic encoder. For finite alphabets, we characterize Renderer-Only Transfer's exact compression-common-randomness rate region, renderer-hull controllability condition, and compression-rate penalty relative to Full Redesign. Under unlimited common randomness, this penalty is the minimum residual semantic information $I(S;U|X)$ forced by the inherited renderer. Representation-Induced Transfer is exact if and only if the semantic condition depends on the source only through the recurrent-class label $C$ of the end-to-end RDP test channel. Every compatible RDP code reused under Full-Model Transfer preserves $C$ and supports every task satisfying $X-C-S$. Any additionally transferable within-class semantic dependence must satisfy $I(S;X|C)\\le R_0-H(C)$, where $R_0$ is the inherited compression rate. The bound is exact when $R_0=H(C)$. A scalar Gaussian specialization yields a renderer-noise controllability threshold, a closed-form transfer penalty, and examples of identical Gaussian RDP test channels with different Renderer-Only Transfer capabilities.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.34697",
  "author_total": 3,
  "authors": [
    {
      "name": "Jinwan Jeon"
    },
    {
      "name": "Seoyeon Hwang"
    },
    {
      "name": "Sung Hoon Lim"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/7awzbmnk1ykgp.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.34697",
  "fulltext_url": null,
  "id": "7awzbmnk1ykgp",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.34697",
  "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.IT"
    ],
    [
      "arxiv",
      "math.IT"
    ],
    [
      "openalex",
      "1707|Advanced Data Compression Techniques"
    ]
  ],
  "openalex": "W7224002690",
  "pdf_url": "https://arxiv.org/pdf/2610.34697",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-26",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/7awzbmnk1ykgp.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:35:40Z",
      "native_id": "2610.34697",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.34697"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.IT",
      "subfield": "general"
    }
  ],
  "title": "Semantic Transferability of Generative Rate-Distortion-Perception Systems",
  "title_text": "Semantic Transferability of Generative Rate-Distortion-Perception Systems",
  "type": "preprint",
  "updated_at": "2026-10-30T12:35:40Z",
  "url": "https://research.draconitic.com/paper/7awzbmnk1ykgp",
  "venue": "arXiv",
  "versions": []
}