Contribution seq 24337

Payload

{
  "ops": [
    {
      "op": "CREATE_SOURCE",
      "ref": "src_nmi_genfocal_2026",
      "title": "Regional climate risk assessment from climate models using probabilistic machine learning",
      "publisher": "Nature Machine Intelligence",
      "source_type": "PRIMARY_TEXT",
      "retrieved_at": "2026-09-29T03:11:10Z",
      "canonical_uri": "https://www.nature.com/articles/s42256-026-01308-7"
    },
    {
      "op": "CREATE_SOURCE_LOCATION",
      "ref": "ex_nmi_genfocal_2026",
      "excerpt": "Here we introduce GenFocal, an AI framework that generates statistically accurate, fine-scale weather from coarse climate projections without requiring paired simulated and observed events during training. GenFocal synthesizes complex and long-lived hazards, such as heatwaves and tropical cyclones, even when they are not well represented in the coarse climate projections.",
      "locator": {},
      "source_id": "src_nmi_genfocal_2026",
      "excerpt_hash": "sha256:daf13ea0a43b525e516e7688d404907dc8139128ee820dc2d4bd85aae138df28",
      "locator_type": "QUOTE"
    },
    {
      "op": "CREATE_EVIDENCE",
      "ref": "ev_nmi_genfocal_support",
      "statement": "The primary Nature Machine Intelligence article directly states that GenFocal produces fine-scale weather from coarse projections without paired simulated/observed training events and synthesizes long-lived heatwaves and tropical cyclones.",
      "observation_type": "DIRECT_TEXT",
      "source_location_id": "ex_nmi_genfocal_2026"
    },
    {
      "op": "LINK_EVIDENCE",
      "note": "The abstract directly covers each substantive component of the claim.",
      "claim_id": "a15ab6bf-718e-8650-8392-6069b5e3e76b",
      "direction": "SUPPORT",
      "evidence_item_id": "ev_nmi_genfocal_support",
      "interpretive_steps": 0,
      "relevance_strength": "DIRECT"
    }
  ],
  "outcome": "FOUND"
}

Rows created

• Source f78d8c1b-bd20-876f-aef3-55e4cbb46a8c
• SourceLocation b9ff35f3-255c-8cd6-b902-e5c5d434f558
• EvidenceItem 4402d624-9a8f-8270-956c-b02c211d7445
• EvidenceClaimLink c81c88a8-81e1-86cb-98d6-c1facd98d6aa (accepted seq 24338)

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}