{
  "$schema": "https://themachinepress.com/schemas/story-v1.schema.json",
  "schema_version": "1.0.0",
  "document_type": "machine_press_story",
  "story": {
    "story_id": "mp-2026-10-01-018",
    "source_story_id": "tmp-sidebar-quantum-linear-threshold-learning",
    "edition_id": "mp-2026-10-01-morning-0084",
    "edition_url": "https://themachinepress.com/edition/2026-10-01",
    "position": 20,
    "story_type": "ticker",
    "section": "research",
    "editorial_classification": "editorial",
    "headline": "Quantum Queries Learned a Threshold With Logarithmic Calls",
    "slug": "quantum-queries-learned-a-threshold-with-logarithmic-calls",
    "dek": "The real-domain algorithm used O(log(n/epsilon)) membership queries where classical methods need a linear factor in n.",
    "summary": "The real-domain algorithm used O(log(n/epsilon)) membership queries where classical methods need a linear factor in n.",
    "body_text": "The paper gives quantum algorithms for learning several linear-threshold-function settings. In the real-domain membership-query model, it uses O(log(n/epsilon)) queries and near-linear additional gates, while its sparse-majority result improves support identification to O(log k) quantum queries under the stated structure.",
    "why_it_matters": "The real-domain algorithm used O(log(n/epsilon)) membership queries where classical methods need a linear factor in n.",
    "limitations": [],
    "importance": 7,
    "canonical_url": "https://themachinepress.com/story/mp-2026-10-01-018/quantum-queries-learned-a-threshold-with-logarithmic-calls",
    "json_url": "https://themachinepress.com/story/mp-2026-10-01-018.json",
    "first_published_at": "2026-10-01T09:00:00.000-04:00",
    "modified_at": "2026-10-01T09:00:00.000-04:00",
    "content_status": "new",
    "is_carryover": false,
    "carryover_reason": null,
    "key_claims": [
      {
        "claim_id": "claim-mp-2026-10-01-018-001",
        "text": "The real-domain algorithm used O(log(n/epsilon)) membership queries where classical methods need a linear factor in n.",
        "source_ids": [
          "source-2026-10-01-020"
        ],
        "qualification": null
      }
    ],
    "source_ids": [
      "source-2026-10-01-020"
    ],
    "tags": [
      "quantum learning",
      "threshold functions",
      "query complexity"
    ],
    "image_url": null,
    "corrections": []
  },
  "sources": [
    {
      "source_id": "source-2026-10-01-020",
      "title": "arXiv preprint 2609.40331",
      "publisher": "arXiv",
      "url": "https://arxiv.org/abs/2609.40331",
      "canonical_url": "https://arxiv.org/abs/2609.40331",
      "source_type": "primary_research",
      "is_primary_source": true,
      "published_at": "2026-09-30T13:56:41.000-04:00",
      "accessed_at": "2026-10-01T08:18:00.000-04:00",
      "supports_claim_ids": [
        "claim-mp-2026-10-01-018-001"
      ]
    }
  ],
  "corrections": [],
  "publisher": {
    "name": "The Machine Press",
    "url": "https://themachinepress.com",
    "description": "A daily newspaper for the age of artificial intelligence."
  },
  "cite_this_report": {
    "title": "Quantum Queries Learned a Threshold With Logarithmic Calls",
    "publisher": "The Machine Press",
    "published_at": "2026-10-01T09:00:00.000-04:00",
    "canonical_url": "https://themachinepress.com/story/mp-2026-10-01-018/quantum-queries-learned-a-threshold-with-logarithmic-calls"
  }
}