{
  "abstract": "Amortized neural posterior estimation fits X-ray spectra in milliseconds, and pipeline use will lean on post-hoc checks to catch detector systematics the simulator misses. We measure what those checks see, on simulated spectra from real XMM-Newton EPIC-pn and NICER responses. Of four misspecification families, an unmodelled 6.4 keV line and partial covering are catchable per spectrum (AUC 0.97 and 0.84). A wrong continuum family reaches 0.66. One flow passed every recovery check yet under-covered (coverage deviation 0.114), and a converged NICER flow (0.011) fails simulation-based calibration on all five parameters. Recovery metrics do not certify calibration. Three schemes catch the line: the posterior-predictive check, importance sampling against the exact Poisson likelihood (effective sample size, 0.68-0.82), and the nested-sampling evidence (count-controlled, $-67$ to $-892$ nats). None catches the 3 per cent gain shift, 2.4 to 14.4 times the EPIC-pn energy-scale accuracy (AUC 0.44-0.54; 36-cell means 0.50 and 0.49 on both responses; paired evidence $+0.33 \\pm 1.37$ nats). The effective sample size stays null-consistent from 0.1 to 10 per cent, realistic amplitudes included. The shift still biases the photon index by $+0.02$ (0.03 to 0.11$σ$) at both count levels. Retraining with a per-simulation nuisance gain adds no inference-time cost, and the gain posterior returns the prior. The bias survives, and exact gain-marginalized nested sampling shows the flow capturing at most 0.163 of its gain constraint (continuous-prior convention) at high counts. Marginalization over posited calibration nuisances is the working defence for X-ray SBI at catalog scale; no check we ran supplies a warning.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2606.17098",
  "author_total": 1,
  "authors": [
    {
      "name": "Karan Akbari"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/9md91g11ha458.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2606.17098",
  "fulltext_url": null,
  "id": "9md91g11ha458",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2606.17098",
  "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",
      "astro-ph.HE"
    ],
    [
      "arxiv",
      "astro-ph.IM"
    ],
    [
      "openalex",
      "3103|Astrophysical Phenomena and Observations"
    ]
  ],
  "openalex": "W7165052152",
  "pdf_url": "https://arxiv.org/pdf/2606.17098",
  "pmcid": null,
  "pmid": null,
  "published": "2026-08-30",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/9md91g11ha458.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:41Z",
      "native_id": "2606.17098",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2606.17098"
    }
  ],
  "subjects": [
    {
      "field": "astronomy",
      "origin": "arxiv:astro-ph.HE",
      "subfield": "high-energy-astrophysics"
    },
    {
      "field": "astronomy",
      "origin": "arxiv:astro-ph.IM",
      "subfield": "instrumentation-methods"
    }
  ],
  "title": "Misspecification in amortized X-ray spectral inference: a detection benchmark, a gain shift three schemes cannot see, and marginalizing it out",
  "title_text": "Misspecification in amortized X-ray spectral inference: a detection benchmark, a gain shift three schemes cannot see, and marginalizing it out",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:41Z",
  "url": "https://research.draconitic.com/paper/9md91g11ha458",
  "venue": "arXiv",
  "versions": []
}