{
  "abstract": "Few-shot adaptation can help or harm single-cell perturbation prediction, but conventional evaluation shares a control estimate between calibration responses and held-out targets. We show how methods carry control error into their predictions and derive its contribution to score inflation. Nested control-depth experiments support inverse-depth scaling of inner-product inflation; correlation inflation also depends on the control noise-to-signal ratio. Independent-control scoring changed the rank of 40 of 52 configuration-dataset entries. We introduce SafeDelta, a split-control criterion that uses calibration data to decide whether to adapt. Across six datasets, mean gated gain was non-negative under the original two-control evaluation. On a deep plate, fixed predictions and decisions retained positive mean gains under three additional independent control references. The same reproducibility principle identified a fibrosis programme that localises to scar in human liver. These results inform adaptation decisions and control-depth planning.",
  "abstract_shown": true,
  "affiliations": [
    "Macau University of Science and Technology, Macau, China; Jinan University, Guangzhou, China; Institute for Intelligent Bioinnovation, Knowledge Transfer Center"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 15,
  "authors": [
    {
      "name": "W.-L. Liang"
    },
    {
      "name": "Y.-B. Yang"
    },
    {
      "name": "Q.-Y. Zhang"
    },
    {
      "name": "J.-C. Feng"
    },
    {
      "name": "Q.-F. Wang"
    },
    {
      "name": "D. Zou"
    },
    {
      "name": "J.-L. Tang"
    },
    {
      "name": "Y. Liu"
    },
    {
      "name": "S.-Y. Wang"
    },
    {
      "name": "J. Duan"
    },
    {
      "name": "Y. Bai"
    },
    {
      "name": "Y.-F. Li"
    },
    {
      "name": "W.-Y. Sun"
    },
    {
      "name": "Y.-F. Cao"
    },
    {
      "affs": [
        0
      ],
      "name": "R.-R. He"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/181gjhr66cf0n.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.10.05.756906",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.10.05.756906v1.full",
  "id": "181gjhr66cf0n",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.10.05.756906v1",
  "language": null,
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "bioinformatics"
    ],
    [
      "openalex",
      "1312|Single-cell and spatial transcriptomics"
    ]
  ],
  "openalex": "W7221663948",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.10.05.756906v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-05",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/181gjhr66cf0n.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:27:34Z",
      "native_id": "10.64898/2026.10.05.756906",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.10.05.756906v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "A split-control criterion for few-shot adaptation in single-cell perturbation prediction",
  "title_text": "A split-control criterion for few-shot adaptation in single-cell perturbation prediction",
  "type": "preprint",
  "updated_at": "2026-10-30T12:27:34Z",
  "url": "https://research.draconitic.com/paper/181gjhr66cf0n",
  "venue": "bioRxiv",
  "versions": []
}