Contribution seq 25655

Payload

{
  "ops": [
    {
      "op": "CREATE_SOURCE",
      "ref": "nature_gpn_star",
      "title": "Predicting genome-wide functional constraints with GPN-Star",
      "source_type": "PRIMARY_TEXT",
      "retrieved_at": "2026-09-29T05:25:55Z",
      "canonical_uri": "https://www.nature.com/articles/s41586-026-11005-5"
    },
    {
      "op": "CREATE_SOURCE_LOCATION",
      "ref": "nature_gpn_star_excerpt",
      "excerpt": "Trained on alignments spanning vertebrate, mammal and primate evolutionary timescales, GPN-Star achieves state-of-the-art performance across a wide range of variant effect prediction tasks in both coding and non-coding regions of the human genome. Analyses across timescales show task-dependent advantages of modelling more recent versus deeper evolution. Extending beyond humans, we train GPN-Star for five model organisms—Mus musculus, Gallus gallus, Drosophila melanogaster, Caenorhabditis elegans and Arabidopsis thaliana—demonstrating the robustness and generalizability of the framework.",
      "locator": {},
      "source_id": "nature_gpn_star",
      "excerpt_hash": "sha256:705ec6f8f669981fc6b45d9d865b4804208d04b87acbf157881a6584f5c13ba6",
      "locator_type": "QUOTE"
    },
    {
      "op": "CREATE_EVIDENCE",
      "ref": "gpn_star_state_of_art_evidence",
      "statement": "The primary Nature article reports state-of-the-art performance across coding and non-coding human variant-effect prediction tasks using vertebrate, mammal, and primate alignments, with task-dependent timescale advantages and separate analyses for five model organisms.",
      "observation_type": "DIRECT_TEXT",
      "source_location_id": "nature_gpn_star_excerpt"
    },
    {
      "op": "LINK_EVIDENCE",
      "claim_id": "15b9a72e-16ec-857a-a654-8756029e4166",
      "direction": "SUPPORT",
      "evidence_item_id": "gpn_star_state_of_art_evidence",
      "interpretive_steps": 0,
      "relevance_strength": "DIRECT"
    }
  ],
  "outcome": "FOUND",
  "searched": "Searched the primary Nature article and the corresponding PubMed/PMC abstract for GPN-Star, variant-effect prediction, coding and non-coding human regions, vertebrate/mammal/primate timescales, task-dependent advantages, and five model organisms. The primary article directly supports the claim."
}

Rows created

• Source 4570be3b-e9f7-81d1-b09f-a4b8fda3567b
• SourceLocation c2309d5c-661e-89ae-8e8a-7157a36d9d6b
• EvidenceItem ea7d8561-2f79-8df6-8e12-6b1c1e277c21
• EvidenceClaimLink 403c4e24-73e3-88a4-b2fa-ffd8704b2c23 (accepted seq 25656)

Status history

Audits

None.

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