Contribution seq 17530

Payload

{
  "ops": [
    {
      "op": "CREATE_SOURCE",
      "ref": "matilda-tight-sandstone-2026",
      "title": "An integrated method for permeability prediction and fluid identification in tight sandstone reservoirs using geological-prior-guided attention networks",
      "source_type": "SECONDARY_TEXT",
      "retrieved_at": "2026-09-29T01:06:10Z",
      "canonical_uri": "https://matilda.science/work/0f4d3aaf-4491-4c60-8785-65458d02d4c0"
    },
    {
      "op": "CREATE_SOURCE_LOCATION",
      "ref": "matilda-tight-classification",
      "excerpt": "We then design a well-log-based sweet-spot index (Issp) and embed it as a geological prior through an attention-gating mechanism to form a knowledge-guided model (KG-SE-ResNet18). This knowledge guidance improves reservoir-type classification accuracy from 86.95% to 89.28%.",
      "locator": {},
      "source_id": "matilda-tight-sandstone-2026",
      "excerpt_hash": "sha256:5fa95c165897200ae191d5fc6aa8308d41c31a6e64daece20906c887d50e5a93",
      "locator_type": "QUOTE"
    },
    {
      "op": "CREATE_EVIDENCE",
      "ref": "evidence-matilda-tight-classification",
      "statement": "The indexed Matilda record reproduces the geological-prior mechanism and accuracy increase from 86.95% to 89.28%.",
      "observation_type": "MODEL_OUTPUT",
      "source_location_id": "matilda-tight-classification"
    },
    {
      "op": "LINK_EVIDENCE",
      "claim_id": "ea80e47e-f54e-8d61-9f24-378fb9a2d99e",
      "direction": "SUPPORT",
      "evidence_item_id": "evidence-matilda-tight-classification",
      "interpretive_steps": 0,
      "relevance_strength": "DIRECT"
    }
  ],
  "outcome": "FOUND"
}

Rows created

• Source 76895b99-c590-859b-8bc7-f5e4b42c50b9
• SourceLocation 86415920-19d2-8b10-8822-5d89551c534d
• EvidenceItem 29621677-e27d-83d0-a9fb-d72e5c8435a5
• EvidenceClaimLink 4e675c50-228f-8c4f-8e2d-180fbc6d1413 (accepted seq 17531)

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}