{
  "abstract": "We revisit a neural negative binomial model for weekly earthquake counts on a 3 x 3 degree grid over the Tian Shan and Pamir, and ask which of its conclusions survive a careful evaluation. At the completeness magnitude of 4.5, the 144-week test period holds 2448 cell-weeks; six cell-weeks, in five distinct weeks, have three or more events. Two conclusions survive. First, Poisson forecasts, temporal ETAS included, understate the probability of such a busy week: ETAS expects 0.72 where six occurred, a shortfall by a factor of 8.3 (p = 0.00009, exact test). One dispersion parameter removes it (ETAS with dispersion expects 4.45, p = 0.58); simulating aftershock chains within the week also reproduces the tail but overshoots the total count by about a quarter. Second, the network's advantage over a linear model disappears once that model has an intercept per cell: the remaining gain is 3.4% of deviance, not significant (p = 0.57 over five test years), and it comes from one cell-week out of the 4420 scored; without it the network is 0.7% worse. A blind test on 2024 to September 2026, with every model fitted on data through 2023, confirms the tail result: Poisson forecasts are rejected (p from 3 x 10^-8 to 0.001), dispersion models are not (p between 0.25 and 0.84), except the NB GLM, whose level blew up out of sample and which is rejected at p = 0.003. Out of sample, model families differ in how they extrapolate beyond the training range, not in the per-cell term. We also measure the evaluation traps met on the way: a biased reference level, a single seed (five of six effects in v1's results table change sign), too few bootstrap resamples, and a threshold below completeness, which shrinks the ETAS shortfall from 8.3 to 2.8 times. This version replaces preprint v1; Section 7 lists the corrections.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2605.21437",
  "author_total": 1,
  "authors": [
    {
      "name": "Alim Igilik"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2wm0ddamtd37y.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2605.21437",
  "fulltext_url": null,
  "id": "2wm0ddamtd37y",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2605.21437",
  "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.LG"
    ],
    [
      "arxiv",
      "physics.geo-ph"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1702|Seismology and Earthquake Studies"
    ]
  ],
  "openalex": "W7161957165",
  "pdf_url": "https://arxiv.org/pdf/2605.21437",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-22",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/2wm0ddamtd37y.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:34:34Z",
      "native_id": "2605.21437",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2605.21437"
    }
  ],
  "subjects": [
    {
      "field": "earth",
      "origin": "arxiv:physics.geo-ph",
      "subfield": "geophysics"
    },
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Evaluating Neural Probabilistic Forecasts of Sparse Earthquake Counts: What Survives a Careful Evaluation",
  "title_text": "Evaluating Neural Probabilistic Forecasts of Sparse Earthquake Counts: What Survives a Careful Evaluation",
  "type": "preprint",
  "updated_at": "2026-10-30T12:34:43Z",
  "url": "https://research.draconitic.com/paper/2wm0ddamtd37y",
  "venue": "arXiv",
  "versions": []
}