{
  "$schema": "https://themachinepress.com/schemas/story-v1.schema.json",
  "schema_version": "1.0.0",
  "document_type": "machine_press_story",
  "story": {
    "story_id": "mp-2026-10-06-008",
    "source_story_id": "tmp-story-time-series-evidence",
    "edition_id": "mp-2026-10-06-morning-0089",
    "edition_url": "https://themachinepress.com/edition/2026-10-06",
    "position": 8,
    "story_type": "dispatch",
    "section": "benchmarks-evals",
    "editorial_classification": "editorial",
    "headline": "The Answer Was Right. The Time Series Was Ignored.",
    "slug": "the-answer-was-right-the-time-series-was-ignored",
    "dek": "Interventions showed that aggregate accuracy could hide whether a QA system used the numerical evidence it was given.",
    "summary": "Interventions showed that aggregate accuracy could hide whether a QA system used the numerical evidence it was given.",
    "body_text": "Researchers evaluated four time-series question-answering systems under the original input and six interventions that changed the supplied numerical series while holding the question and target fixed. Similar task-level scores often concealed substantial changes in individual predictions, and some systems fell back to simple behaviors rather than preserving the claimed capability. An audit of rationales also found numerical claims unsupported by the input and intermediate inferences that were invalid even when the explanation agreed with the final answer. The benchmark's warning is broader than time series: correct outputs do not establish that a system read, used or faithfully described its evidence.",
    "why_it_matters": "Interventions showed that aggregate accuracy could hide whether a QA system used the numerical evidence it was given.",
    "limitations": [
      "The benchmark's warning is broader than time series: correct outputs do not establish that a system read, used or faithfully described its evidence."
    ],
    "importance": 8,
    "canonical_url": "https://themachinepress.com/story/mp-2026-10-06-008/the-answer-was-right-the-time-series-was-ignored",
    "json_url": "https://themachinepress.com/story/mp-2026-10-06-008.json",
    "first_published_at": "2026-10-06T09:00:00.000-04:00",
    "modified_at": "2026-10-06T09:00:00.000-04:00",
    "content_status": "new",
    "is_carryover": false,
    "carryover_reason": null,
    "key_claims": [
      {
        "claim_id": "claim-mp-2026-10-06-008-001",
        "text": "Interventions showed that aggregate accuracy could hide whether a QA system used the numerical evidence it was given.",
        "source_ids": [
          "source-2026-10-06-008"
        ],
        "qualification": "The benchmark's warning is broader than time series: correct outputs do not establish that a system read, used or faithfully described its evidence."
      }
    ],
    "source_ids": [
      "source-2026-10-06-008"
    ],
    "tags": [
      "time series",
      "question answering",
      "evidence use"
    ],
    "image_url": "https://themachinepress.com/issues/2026-10-06/time-series-code-monitor.webp",
    "corrections": []
  },
  "sources": [
    {
      "source_id": "source-2026-10-06-008",
      "title": "arXiv preprint 2610.05686",
      "publisher": "arXiv",
      "url": "https://arxiv.org/abs/2610.05686",
      "canonical_url": "https://arxiv.org/abs/2610.05686",
      "source_type": "primary_research",
      "is_primary_source": true,
      "published_at": "2026-10-04T21:59:38.000-04:00",
      "accessed_at": "2026-10-06T08:25:42.165-04:00",
      "supports_claim_ids": [
        "claim-mp-2026-10-06-008-001"
      ]
    }
  ],
  "corrections": [],
  "publisher": {
    "name": "The Machine Press",
    "url": "https://themachinepress.com",
    "description": "A daily newspaper for the age of artificial intelligence."
  },
  "cite_this_report": {
    "title": "The Answer Was Right. The Time Series Was Ignored.",
    "publisher": "The Machine Press",
    "published_at": "2026-10-06T09:00:00.000-04:00",
    "canonical_url": "https://themachinepress.com/story/mp-2026-10-06-008/the-answer-was-right-the-time-series-was-ignored"
  }
}