{
  "abstract": "Predicting cellular responses to genetic perturbations helps prioritize experiments in single-cell genomics, where exhaustive measurement is infeasible. While computational models increasingly predict these responses, three evaluation deficiencies obscure what their scores demonstrate. First, absolute metrics cannot separate target-specific predictions from a shared background response. Second, common metrics remain high under gene shuffling, so gene-level accuracy is never verified. Third, a score at one training size says nothing about coverage, which depends on representation-space proximity and response-constraining power. We propose AmbiModBench, a specificity-aware, gene-resolved and coverage-aware benchmark. It pairs every score with a training-mean reference fitted on the same split, screens each readout by gene-coordinate permutation, and links embedding distance to response variation. Across K562, RPE1 and Norman, strong absolute scores largely reflect shared background rather than target-specific learning. Widely used readouts track response magnitude distributions rather than the affected genes. Detectable gain follows representation-space coverage rather than training-set size. Nonetheless, on RPE1 the protocol yields a reproducible target-specific gain across five additional splits and three gene selections, which absolute scores alone cannot distinguish from shared background.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.32527",
  "author_total": 5,
  "authors": [
    {
      "name": "Sikai Huang"
    },
    {
      "name": "Zhiwen Yang"
    },
    {
      "name": "Kai Yu"
    },
    {
      "name": "Jiayuan Chen"
    },
    {
      "name": "Stan Z. Li"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/7gw38kxsk17x2.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.32527",
  "fulltext_url": null,
  "id": "7gw38kxsk17x2",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.32527",
  "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.AI"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "q-bio.GN"
    ],
    [
      "arxiv",
      "stat.AP"
    ],
    [
      "openalex",
      "1312|Gene Regulatory Network Analysis"
    ]
  ],
  "openalex": "W7214779028",
  "pdf_url": "https://arxiv.org/pdf/2609.32527",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-26",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/7gw38kxsk17x2.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:25:21Z",
      "native_id": "2609.32527",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.32527"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.GN",
      "subfield": "genetics-genomics"
    },
    {
      "field": "mathematics",
      "origin": "arxiv:stat.AP",
      "subfield": "statistics"
    }
  ],
  "title": "AmbiModBench: Benchmarking Gene Perturbation Prediction Beyond Shared Responses",
  "title_text": "AmbiModBench: Benchmarking Gene Perturbation Prediction Beyond Shared Responses",
  "type": "preprint",
  "updated_at": "2026-10-30T12:25:26Z",
  "url": "https://research.draconitic.com/paper/7gw38kxsk17x2",
  "venue": "arXiv",
  "versions": []
}