{
  "abstract": "When an image classifier decides, we can usually only estimate why. For quantum and all-optical classifiers that act linearly on amplitude-encoded pictures up to the measurement, with no trained classical network before or after them, each class's Born probability above its no-information share, $P_g - b_g$, splits exactly into contributions of the encoded amplitudes, shown as Born evidence maps (BEM) over the picture. The split itself follows from known results on quadratic forms: with the transmitted light held fixed, it is what Integrated Gradients from a zero baseline and the Shapley value give. What we add is a way to measure it on the hardware that classifies, from class probabilities on a quantum chip or from camera frames on a lens bench, with no gradient circuit and no light sent backwards; a $g\\times g$ map takes $1 + 2g^2$ runs. Deleting the 5% of pixels with the highest evidence drops accuracy from 73% to 9%, as occlusion does with 1,024 extra runs per picture, whereas gradient saliency removes much less. The classifiers share one architecture, a Fourier-plane mask followed by a brickwall circuit on qubits or by phase plates on a lens bench, read by a fixed Born headroom readout with no trained parameter; centring each picture on its own mean lets dark features count as much as bright ones. In simulation, four phase plates at a single wavelength reach 72.3% on Caltech-10 colour photographs. On IBM's ibm_kingston, with the mask applied before approximate loading, 300 test pictures were classified at 37.7% against 10% by chance (56.3% in exact simulation), and $2\\times2$ maps of ten correctly classified pictures, one per class chosen by a stated rule, measured on the chip, agreed with the exact ones ($r = 0.77$). The maps also revealed a shortcut in the data; as the trim that removed it was chosen on test pictures, the Caltech-10 results are exploratory.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2611.01993",
  "author_total": 2,
  "authors": [
    {
      "name": "Teerawat Tongloy"
    },
    {
      "name": "Rangsan Jomtarak"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2svhw5aby5abn.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2611.01993",
  "fulltext_url": null,
  "id": "2svhw5aby5abn",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2611.01993",
  "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",
      "physics.optics"
    ],
    [
      "arxiv",
      "quant-ph"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2611.01993",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/2svhw5aby5abn.ris",
  "sources": [
    {
      "first_seen": "2026-11-03T12:20:59Z",
      "native_id": "2611.01993",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2611.01993"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:physics.optics",
      "subfield": "optics-photonics"
    },
    {
      "field": "physics",
      "origin": "arxiv:quant-ph",
      "subfield": "quantum"
    }
  ],
  "title": "Seeing Why: Exact Evidence Maps for Quantum and Optical Image Classifiers",
  "title_text": "Seeing Why: Exact Evidence Maps for Quantum and Optical Image Classifiers",
  "type": "preprint",
  "updated_at": "2026-11-09T00:20:39Z",
  "url": "https://research.draconitic.com/paper/2svhw5aby5abn",
  "venue": "arXiv",
  "versions": []
}