{
  "$schema": "https://themachinepress.com/schemas/story-v1.schema.json",
  "schema_version": "1.0.0",
  "document_type": "machine_press_story",
  "story": {
    "story_id": "mp-2026-11-09-014",
    "source_story_id": "tmp-story-ucr-provenance-audit",
    "edition_id": "mp-2026-11-09-morning-0122",
    "edition_url": "https://themachinepress.com/edition/2026-11-09",
    "position": 14,
    "story_type": "dispatch",
    "section": "benchmarks-evals",
    "editorial_classification": "editorial",
    "headline": "A Benchmark Asked Which Pig Made the Trace",
    "slug": "a-benchmark-asked-which-pig-made-the-trace",
    "dek": "A provenance audit finds repurposed tasks, toy setups and flawed splits inside a standard time-series archive.",
    "summary": "A provenance audit finds repurposed tasks, toy setups and flawed splits inside a standard time-series archive.",
    "body_text": "PigAirwayPressure began as a hemorrhage-detection experiment, yet its UCR Archive task asks a classifier to identify which of 52 pigs produced a trace. The authors trace this and other datasets back to their origins, finding repurposed objectives, toy setups, questionable splits and ordered non-temporal sequences presented as time-series tasks. They also question whether decomposing multivariate problems preserves the deployment setting. The audit does not invalidate every archive-wide comparison, but it shows why aggregate benchmark ranks can reward performance on tasks that differ materially from the practical questions the source data were collected to answer.",
    "why_it_matters": "A provenance audit finds repurposed tasks, toy setups and flawed splits inside a standard time-series archive.",
    "limitations": [
      "The audit does not invalidate every archive-wide comparison, but it shows why aggregate benchmark ranks can reward performance on tasks that differ materially from the practical questions the source data were collected to answer."
    ],
    "importance": 8,
    "canonical_url": "https://themachinepress.com/story/mp-2026-11-09-014/a-benchmark-asked-which-pig-made-the-trace",
    "json_url": "https://themachinepress.com/story/mp-2026-11-09-014.json",
    "first_published_at": "2026-11-09T09:00:00.000-05:00",
    "modified_at": "2026-11-09T09:00:00.000-05:00",
    "content_status": "new",
    "is_carryover": false,
    "carryover_reason": null,
    "key_claims": [
      {
        "claim_id": "claim-mp-2026-11-09-014-001",
        "text": "A provenance audit finds repurposed tasks, toy setups and flawed splits inside a standard time-series archive.",
        "source_ids": [
          "source-2026-11-09-014"
        ],
        "qualification": "The audit does not invalidate every archive-wide comparison, but it shows why aggregate benchmark ranks can reward performance on tasks that differ materially from the practical questions the source data were collected to answer."
      }
    ],
    "source_ids": [
      "source-2026-11-09-014"
    ],
    "tags": [
      "time series",
      "benchmarks",
      "dataset provenance"
    ],
    "image_url": null,
    "corrections": []
  },
  "sources": [
    {
      "source_id": "source-2026-11-09-014",
      "title": "arXiv preprint 2611.09843, original v1",
      "publisher": "arXiv",
      "url": "https://arxiv.org/abs/2611.09843v1",
      "canonical_url": "https://arxiv.org/abs/2611.09843v1",
      "source_type": "primary_research",
      "is_primary_source": true,
      "published_at": "2026-11-06T13:28:12.000-05:00",
      "accessed_at": "2026-11-09T08:25:54.496-05:00",
      "supports_claim_ids": [
        "claim-mp-2026-11-09-014-001"
      ]
    }
  ],
  "corrections": [],
  "publisher": {
    "name": "The Machine Press",
    "url": "https://themachinepress.com",
    "description": "A daily newspaper for the age of artificial intelligence."
  },
  "cite_this_report": {
    "title": "A Benchmark Asked Which Pig Made the Trace",
    "publisher": "The Machine Press",
    "published_at": "2026-11-09T09:00:00.000-05:00",
    "canonical_url": "https://themachinepress.com/story/mp-2026-11-09-014/a-benchmark-asked-which-pig-made-the-trace"
  }
}