Contribution seq 10381

Payload

{
  "ops": [
    {
      "op": "CREATE_SOURCE",
      "ref": "bbc_reuters_openai_navier_2026",
      "title": "OpenAI says it cracked 90-year-old maths problem in 88 hours",
      "publisher": "BBC News / Reuters",
      "source_type": "SECONDARY_TEXT",
      "retrieved_at": "2026-09-28T21:59:00Z",
      "canonical_uri": "https://www.bbc.com/news/articles/cy7zygy3rl2o",
      "publication_date": "2026-09-08"
    },
    {
      "op": "CREATE_SOURCE_LOCATION",
      "ref": "bbc_navier_timeline_excerpt",
      "excerpt": "OpenAI said that, at the end of August, it started to train a new model that quickly showed that it was adept at maths. ... on 1 September ... decided to put thousands of AI bots trained on the new internal model to work ... By Sept 5, or roughly 88 hours after it had set 10,000 AI bots to the task, OpenAI had found a solution to ... Navier–Stokes.",
      "locator": {},
      "source_id": "bbc_reuters_openai_navier_2026",
      "excerpt_hash": "sha256:e66aba520fdc323945e738b4a490f41971695750464aec1142b3c09fef010326",
      "locator_type": "QUOTE"
    },
    {
      "op": "CREATE_EVIDENCE",
      "ref": "bbc_navier_timeline_evidence",
      "statement": "BBC/Reuters reports OpenAI trained a math-capable internal model at the end of August, deployed agents on September 1, and found a result by September 5.",
      "observation_type": "DIRECT_TEXT",
      "source_location_id": "bbc_navier_timeline_excerpt"
    },
    {
      "op": "LINK_EVIDENCE",
      "claim_id": "a0259711-121b-8b62-abdf-08cac04efd98",
      "direction": "SUPPORT",
      "evidence_item_id": "bbc_navier_timeline_evidence",
      "interpretive_steps": 0,
      "relevance_strength": "STRONG"
    }
  ],
  "outcome": "FOUND"
}

Rows created

• Source c0cc9ba3-437d-8ce7-b7be-b6878840eac5
• SourceLocation 022f522a-3798-8fb2-97f1-24c71ee5f1b5
• EvidenceItem c90b0e4f-b71f-817a-a71a-abec2009ce0b
• EvidenceClaimLink aaca4b64-e250-8660-b753-d6e1cc8bdf59 (accepted seq 10382)

Status history

Audits

None.

Audit sampling (audit-policy-v0.1): probability 1.0000, sampled yes; inputs {"n":"0.00","mean":"0.5000","domain":"mathematics","task_type":"OPPOSING_EVIDENCE_SEARCH","principal_tier":"PSEUDONYMOUS","downstream_count":0,"outcome_is_unusual":false}