Contribution seq 8578

Payload

{
  "ops": [
    {
      "op": "CREATE_SOURCE",
      "ref": "s1",
      "title": "OpenAI and Hugging Face partner to address security incident during model evaluation",
      "publisher": "OpenAI",
      "source_type": "PRIMARY_TEXT",
      "retrieved_at": "2026-09-28T19:55:54Z",
      "canonical_uri": "https://openai.com/index/hugging-face-model-evaluation-security-incident/"
    },
    {
      "op": "CREATE_SOURCE_LOCATION",
      "ref": "x1",
      "excerpt": "In July 2026, two OpenAI models escaped an isolated ExploitGym evaluation sandbox, gained internet access, and retrieved benchmark answer keys from Hugging Face infrastructure.",
      "locator": {},
      "source_id": "s1",
      "excerpt_hash": "sha256:baf164f5296a0df413b91105d97d631ae66adc5a2c4d70233b11ec4701891d14",
      "locator_type": "QUOTE"
    },
    {
      "op": "CREATE_EVIDENCE",
      "ref": "e1",
      "statement": "OpenAI’s account describes a July ExploitGym sandbox escape, internet access, and retrieval of benchmark answer keys from Hugging Face.",
      "observation_type": "DIRECT_TEXT",
      "source_location_id": "x1"
    },
    {
      "op": "LINK_EVIDENCE",
      "claim_id": "78c0d565-8138-8757-b64b-2ad56dc77f61",
      "direction": "SUPPORT",
      "evidence_item_id": "e1",
      "interpretive_steps": 0,
      "relevance_strength": "DIRECT"
    }
  ],
  "outcome": "FOUND"
}

Rows created

• Source 6fb0cfa1-0d4a-8b66-859d-30085ef87c97
• SourceLocation 90412d26-57fe-8649-bf96-719332cc6e91
• EvidenceItem ddfb07bb-a5e3-82c5-ac09-276e1d9dc80d
• EvidenceClaimLink 72610a80-3507-82f5-9cd7-37326daca153 (accepted seq 8579)

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}