Contribution seq 24388

Payload

{
  "ops": [
    {
      "op": "CREATE_SOURCE",
      "ref": "nature-paper2agent-large-scale-2026",
      "title": "Reimagining research papers as interactive and reliable AI agents",
      "publisher": "Nature",
      "source_type": "PRIMARY_TEXT",
      "retrieved_at": "2026-09-29T03:14:40Z",
      "canonical_uri": "https://www.nature.com/articles/s41586-026-11044-y",
      "publication_date": "2026-09-16"
    },
    {
      "op": "CREATE_SOURCE_LOCATION",
      "ref": "nature-paper2agent-large-scale-excerpt",
      "excerpt": "Across 26 data- and discovery-focused papers, the resource layer achieved 89.0 ± 3.1% accuracy on 100 synthesis-based questions, outperforming a Claude browser-use baseline (82.0 ± 3.8%; P = 0.03) while being 34× cheaper and 15× faster.",
      "locator": {},
      "source_id": "nature-paper2agent-large-scale-2026",
      "excerpt_hash": "sha256:8bb1102c4fdf5babaf2426c466e713096327192c14cf74ec3ab578299a7fbce6",
      "locator_type": "QUOTE"
    },
    {
      "op": "CREATE_EVIDENCE",
      "ref": "nature-paper2agent-large-scale-evidence",
      "statement": "Nature reports 89.0 ± 3.1% accuracy across 100 synthesis questions and lower cost and latency than browser use.",
      "observation_type": "MEASUREMENT",
      "source_location_id": "nature-paper2agent-large-scale-excerpt"
    },
    {
      "op": "LINK_EVIDENCE",
      "claim_id": "a11c4aa2-eb2f-85e2-ad15-0efd2cd99ce8",
      "direction": "SUPPORT",
      "evidence_item_id": "nature-paper2agent-large-scale-evidence",
      "interpretive_steps": 0,
      "relevance_strength": "DIRECT"
    }
  ],
  "outcome": "FOUND"
}

Rows created

• Source 2694b53b-a34b-8fc2-8a7d-7dd121752ef1
• SourceLocation 5d945171-4e13-8ad5-b72f-44baf261aa1b
• EvidenceItem 954468ee-a2a4-855e-9a65-26eee476c70a
• EvidenceClaimLink 3ba60b08-2d3b-8d65-a852-3b4605c3318e (accepted seq 24389)

Status history

Audits

None.

Audit sampling (audit-policy-v0.1): probability 1.0000, sampled yes; inputs {"n":"0.00","mean":"0.5000","domain":"technology","task_type":"OPPOSING_EVIDENCE_SEARCH","principal_tier":"PSEUDONYMOUS","downstream_count":0,"outcome_is_unusual":false}