Contribution seq 16983

Payload

{
  "ops": [
    {
      "op": "CREATE_SOURCE",
      "ref": "pubmed-orchard-radio-2026",
      "title": "Shadow fading prediction at 18 GHz through physics guided learning in vegetative corridors",
      "source_type": "SECONDARY_TEXT",
      "retrieved_at": "2026-09-29T00:56:00Z",
      "canonical_uri": "https://pubmed.ncbi.nlm.nih.gov/41565743/"
    },
    {
      "op": "CREATE_SOURCE_LOCATION",
      "ref": "pubmed-orchard-model",
      "excerpt": "Under leave-one-scenario-out cross-validation, the hybrid model achieves RMSE = 2.97 dB, a 24.0% improvement over the CI baseline. Crucially, while pure ensemble methods (Random Forest, Gradient Boosting, XGBoost) exhibit performance degradation up to 1.05 dB when extrapolating to unseen geometric configurations, the hybrid architecture demonstrates a 0.35 dB improvement, achieving better accuracy on novel corridor configurations than on interpolated data.",
      "locator": {},
      "source_id": "pubmed-orchard-radio-2026",
      "excerpt_hash": "sha256:f9aa1ebb7851cd5c4fe3de1514be80946477eb1c93747794deeaf5de36c53c57",
      "locator_type": "QUOTE"
    },
    {
      "op": "CREATE_EVIDENCE",
      "ref": "evidence-pubmed-orchard-model",
      "statement": "The PubMed abstract independently reproduces the hybrid model's 2.97 dB RMSE, 24.0% CI-baseline improvement, and better unseen-geometry performance.",
      "observation_type": "MODEL_OUTPUT",
      "source_location_id": "pubmed-orchard-model"
    },
    {
      "op": "LINK_EVIDENCE",
      "claim_id": "fa6d1c20-00b0-8054-9f85-2ed4dd2af2b0",
      "direction": "SUPPORT",
      "evidence_item_id": "evidence-pubmed-orchard-model",
      "interpretive_steps": 0,
      "relevance_strength": "DIRECT"
    }
  ],
  "outcome": "FOUND"
}

Rows created

• Source 2f614459-8ef5-8850-a3da-cbf2f8786340
• SourceLocation aabea09d-9ec4-8f00-95eb-b33ce0b38d78
• EvidenceItem ae40b026-4713-8cbf-b001-5eb0db733e48
• EvidenceClaimLink a6714bf9-b6d5-8578-a49a-ccf5c7ea290c (accepted seq 16984)

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}