{
  "$schema": "https://themachinepress.com/schemas/story-v1.schema.json",
  "schema_version": "1.0.0",
  "document_type": "machine_press_story",
  "story": {
    "story_id": "mp-2026-09-12-005",
    "source_story_id": "tmp-story-semverbench-version-constraints",
    "edition_id": "mp-2026-09-12-morning-0065",
    "edition_url": "https://themachinepress.com/edition/2026-09-12",
    "position": 5,
    "story_type": "dispatch",
    "section": "developer-tools",
    "editorial_classification": "editorial",
    "headline": "Every Model Tripped Over Cargo’s Carry Rule",
    "slug": "every-model-tripped-over-cargo-s-carry-rule",
    "dek": "SemVerBench found predictable version-constraint blind spots across npm, PEP 440 and Cargo—and a resolver solved the task.",
    "summary": "SemVerBench found predictable version-constraint blind spots across npm, PEP 440 and Cargo—and a resolver solved the task.",
    "body_text": "SemVerBench contains 240 machine-checkable version-constraint questions with unique answers across npm, Python’s PEP 440 and Cargo. Six frontier models showed mechanism-specific failures: Cargo’s partial-comparator carry rule trapped every model near 60%, while a PEP 440 corner set split one model’s 0-of-26 result from another’s 97–100%. Supplying the governing rule recovered many errors; interval decomposition did not. Because a free resolver was effectively perfect, the authors recommend tool delegation over in-head version reasoning.",
    "why_it_matters": "SemVerBench found predictable version-constraint blind spots across npm, PEP 440 and Cargo—and a resolver solved the task.",
    "limitations": [
      "Supplying the governing rule recovered many errors; interval decomposition did not."
    ],
    "importance": 8,
    "canonical_url": "https://themachinepress.com/story/mp-2026-09-12-005/every-model-tripped-over-cargo-s-carry-rule",
    "json_url": "https://themachinepress.com/story/mp-2026-09-12-005.json",
    "first_published_at": "2026-09-12T09:00:00.000-04:00",
    "modified_at": "2026-09-12T09:00:00.000-04:00",
    "content_status": "new",
    "is_carryover": false,
    "carryover_reason": null,
    "key_claims": [
      {
        "claim_id": "claim-mp-2026-09-12-005-001",
        "text": "SemVerBench found predictable version-constraint blind spots across npm, PEP 440 and Cargo—and a resolver solved the task.",
        "source_ids": [
          "source-2026-09-12-005"
        ],
        "qualification": "Supplying the governing rule recovered many errors; interval decomposition did not."
      }
    ],
    "source_ids": [
      "source-2026-09-12-005"
    ],
    "tags": [
      "coding agents",
      "semantic versioning",
      "benchmarks"
    ],
    "image_url": null,
    "corrections": []
  },
  "sources": [
    {
      "source_id": "source-2026-09-12-005",
      "title": "arXiv preprint 2609.11180",
      "publisher": "arXiv",
      "url": "https://arxiv.org/abs/2609.11180",
      "canonical_url": "https://arxiv.org/abs/2609.11180",
      "source_type": "primary_research",
      "is_primary_source": true,
      "published_at": null,
      "accessed_at": "2026-09-12T08:27:00.000-04:00",
      "supports_claim_ids": [
        "claim-mp-2026-09-12-005-001"
      ]
    }
  ],
  "corrections": [],
  "publisher": {
    "name": "The Machine Press",
    "url": "https://themachinepress.com",
    "description": "A daily newspaper for the age of artificial intelligence."
  },
  "cite_this_report": {
    "title": "Every Model Tripped Over Cargo’s Carry Rule",
    "publisher": "The Machine Press",
    "published_at": "2026-09-12T09:00:00.000-04:00",
    "canonical_url": "https://themachinepress.com/story/mp-2026-09-12-005/every-model-tripped-over-cargo-s-carry-rule"
  }
}