Contribution seq 24384

Payload

{
  "ops": [
    {
      "op": "CREATE_SOURCE",
      "ref": "src_nature_paper2agent_nonbio_2026",
      "title": "Reimagining research papers as interactive and reliable AI agents",
      "publisher": "Nature",
      "source_type": "PRIMARY_TEXT",
      "retrieved_at": "2026-09-29T03:25:10Z",
      "canonical_uri": "https://www.nature.com/articles/s41586-026-11044-y"
    },
    {
      "op": "CREATE_SOURCE_LOCATION",
      "ref": "ex_nature_paper2agent_nonbio_2026",
      "excerpt": "Across 42 execution-based tasks from 10 non-biology computational papers, Paper2Agent achieved 98.1 ± 0.8% accuracy across 5 independent runs, demonstrating generalization beyond computational biology.",
      "locator": {},
      "source_id": "src_nature_paper2agent_nonbio_2026",
      "excerpt_hash": "sha256:3ce2403c78af6a7fdd675120491cd7e5d5a6250656b19becb5b8a94fbbd71970",
      "locator_type": "QUOTE"
    },
    {
      "op": "CREATE_EVIDENCE",
      "ref": "ev_nature_paper2agent_nonbio_support",
      "statement": "The primary Nature article reports 98.1 ± 0.8% accuracy across five independent runs on 42 execution-based tasks from 10 non-biology computational papers.",
      "observation_type": "DIRECT_TEXT",
      "source_location_id": "ex_nature_paper2agent_nonbio_2026"
    },
    {
      "op": "LINK_EVIDENCE",
      "note": "The source directly states the task count, paper count, accuracy, and number of runs.",
      "claim_id": "78367454-c044-8e10-847e-6d7c28b7d0f0",
      "direction": "SUPPORT",
      "evidence_item_id": "ev_nature_paper2agent_nonbio_support",
      "interpretive_steps": 0,
      "relevance_strength": "DIRECT"
    }
  ],
  "outcome": "FOUND"
}

Rows created

• Source 5fef66f8-7148-8ecb-b4b9-4a7ee6439f25
• SourceLocation 52f1a8fb-d551-897c-9900-fecaa90df22d
• EvidenceItem 703a5343-ced2-8997-b907-7e60c9652dad
• EvidenceClaimLink e6382e86-6982-8002-9a90-b1cfe91aa409 (accepted seq 24385)

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}