{
  "abstract": "Quantum transfer learning (QTL) is often evaluated by replacing a classical classifier with a fixed variational quantum head, but this hides a key question: when is the quantum branch actually useful? We propose QSTAR: Quantum Selective Transfer with Adaptive Routing, a selective QTL framework that keeps high-confidence classical predictions and routes only low-confidence samples to a fallback branch. Using a frozen ResNet18 backbone on Fashion-MNIST, we compare manually designed QTL heads, KetGPT-designed quantum heads, and parameter-matched classical baselines under a common data split and optimization schedule. Standard QTL heads reach at most 57.0% accuracy, while the strongest KetGPT head in the main filtered sweep reaches 78.5% accuracy and 0.785 F1-score. Although the strongest fixed classical head remains higher at 81.6%, selective routing gives the quantum branch a clearer role. On low-confidence samples, KetGPT #180 improves accuracy over a parameter-matched MLP fallback by 6.82, 4.31, and 3.03 percentage points at thresholds of 0.70, 0.80, and 0.90. At the full-system level, Adaptive KetGPT-QTL reaches 80.9% accuracy and 0.807 F1-score, outperforming the adaptive classical baseline. A separate compact-circuit ablation identifies KetGPT #160 as a stronger fixed-head candidate, reaching 81.9% accuracy with only 10 quantum parameters and 9 gates. These results suggest that architecture-searched quantum heads are most useful as targeted fallback branches for uncertain inputs rather than uniform replacements for classical classifiers.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2607.21411",
  "author_total": 3,
  "authors": [
    {
      "name": "Saim Rehman"
    },
    {
      "name": "Nouhaila Innan"
    },
    {
      "name": "Muhammad Shafique"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/bwgdsg3c89f2e.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2607.21411",
  "fulltext_url": null,
  "id": "bwgdsg3c89f2e",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2607.21411",
  "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",
      "quant-ph"
    ],
    [
      "openalex",
      "1702|Quantum Computing Algorithms and Architecture"
    ]
  ],
  "openalex": "W7170821628",
  "pdf_url": "https://arxiv.org/pdf/2607.21411",
  "pmcid": null,
  "pmid": null,
  "published": "2026-07-23",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/bwgdsg3c89f2e.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:21:25Z",
      "native_id": "2607.21411",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2607.21411"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:quant-ph",
      "subfield": "quantum"
    }
  ],
  "title": "QSTAR: Quantum Selective Transfer with Adaptive Routing",
  "title_text": "QSTAR: Quantum Selective Transfer with Adaptive Routing",
  "type": "preprint",
  "updated_at": "2026-10-30T12:21:25Z",
  "url": "https://research.draconitic.com/paper/bwgdsg3c89f2e",
  "venue": "arXiv",
  "versions": []
}