{
  "id": "AIBD-0070",
  "title": "AlphaProof and AlphaGeometry 2 reach silver-medal standard on IMO 2024 problems, graded by two IMO gold medallists; IMO-certified gold follows in 2025",
  "summary": "DeepMind AI scored 28/42 on IMO 2024 problems, graded by Gowers and Myers; Gemini Deep Think's 35/42 in 2025 was IMO-certified gold",
  "date_observed": "2024-07-25",
  "date_basis": "unassessed",
  "date_precision": "unassessed",
  "benefit_status": null,
  "source_collection": null,
  "source_entry": null,
  "account": "Google DeepMind's AlphaProof (reinforcement learning over the Lean proof language) and AlphaGeometry 2 produced solutions to four of the six 2024 International Mathematical Olympiad problems. Because the systems work in formal language, the problems were first translated manually into Lean. One problem was solved within minutes and others took up to three days, longer than the contest allows. Two former IMO gold medalists, Sir Timothy Gowers and Joseph Myers, graded the solutions under IMO rules. They awarded 28 of 42 points, a silver-medal score. DeepMind announced the result on 25 July 2024 (grading date not given). In July 2025 a Gemini Deep Think model working in natural language within the time limit scored 35 of 42. IMO president Gregor Dolinar confirmed this as a gold-medal score. Nature reported that OpenAI also claimed a gold-level result.",
  "category": "general benefit",
  "unexpected": false,
  "purpose": "Solve competition mathematics problems with machine-checkable formal proofs",
  "system": "AlphaProof and AlphaGeometry 2",
  "model_version": "AlphaProof (2024) and AlphaGeometry 2; 2025 echo: advanced Gemini Deep Think",
  "developer": "DeepMind",
  "deployer": "DeepMind",
  "location": null,
  "domain": "Mathematics competitions",
  "segment": "Olympiad mathematics",
  "benefit_type": "Improved Task Accuracy",
  "taxonomy_note": "A graded competition score is read as task performance; no deployment or user is involved.",
  "registry_ids": {},
  "ratings": [
    {
      "group": "organizational",
      "depth": null,
      "reason": "A capability evaluation on IMO 2024 problems for the developer and the IMO community. The sources describe grading and scores, not a deployment or an observed organizational change."
    },
    {
      "group": "societal",
      "depth": null,
      "reason": "Proofs of already-solved contest problems graded correct, with no identifiable beneficiary beyond the research community. Scientific American notes around 60 students scored better in 2024."
    }
  ],
  "ai_role": {
    "status": "assessed",
    "statement": "The AI systems produced the proofs. Humans manually formalized the 2024 problem statements into Lean (Scientific American) and graded the output. In 2024 the solutions were graded by two mathematicians at DeepMind's request (one of them, Myers, chaired the IMO 2024 Problem Selection Committee). The result was not officially certified by the IMO. DeepMind states the 2025 result was graded and certified by IMO coordinators, with the IMO president's confirmation appearing in the vendor blog. The cited sources do not state whether OpenAI's 2025 claim was certified by the IMO."
  },
  "evidence": [
    {
      "kind": "news report",
      "citation": "Bischoff, M. (2024). AI Reaches Silver-Medal Level at This Year's Math Olympiad. Scientific American.",
      "title": "AI Reaches Silver-Medal Level at This Year's Math Olympiad",
      "url": "https://www.scientificamerican.com/article/ai-reaches-silver-medal-level-at-this-years-math-olympiad/",
      "date": "2024-08-06",
      "written_by": "independent",
      "quote": "Gowers and mathematician Joseph K. Myers, another previous gold medalist, evaluated the solutions of the two AI systems using the same criteria as was used for the human participants."
    },
    {
      "kind": "news report",
      "citation": "Williams, R. (2024). Google DeepMind's new AI systems can now solve complex math problems. MIT Technology Review.",
      "title": "Google DeepMind's new AI systems can now solve complex math problems",
      "url": "https://www.technologyreview.com/2024/07/25/1095315/google-deepminds-ai-systems-can-now-solve-complex-math-problems/",
      "date": "2024-07-25",
      "written_by": "independent",
      "quote": "They awarded each of their four correct answers full marks (seven out of seven), giving the systems a total of 28 points out of a maximum of 42."
    },
    {
      "kind": "news report",
      "citation": "Castelvecchi, D. (2024). DeepMind hits milestone in solving maths problems — AI's next grand challenge. Nature.",
      "title": "DeepMind hits milestone in solving maths problems — AI's next grand challenge",
      "url": "https://www.nature.com/articles/d41586-024-02441-2",
      "date": "2024-07-25",
      "written_by": "independent",
      "quote": "AlphaProof showed its prowess on questions from this year's Mathematical Olympiad — a step in the race to create substantial proofs with artificial intelligence."
    },
    {
      "kind": "press release",
      "citation": "Google DeepMind (2024). AI achieves silver-medal standard solving International Mathematical Olympiad problems. Google DeepMind blog.",
      "title": "AI achieves silver-medal standard solving International Mathematical Olympiad problems",
      "url": "https://deepmind.google/discover/blog/ai-solves-imo-problems-at-silver-medal-level/",
      "date": "2024-07-25",
      "written_by": "makers",
      "quote": "Our system achieved a final score of 28 points, earning a perfect score on each problem solved"
    },
    {
      "kind": "news report",
      "citation": "Castelvecchi, D. (2025). DeepMind and OpenAI models solve maths problems at level of top students. Nature.",
      "title": "DeepMind and OpenAI models solve maths problems at level of top students",
      "url": "https://www.nature.com/articles/d41586-025-02343-x",
      "date": "2025-07-24",
      "written_by": "independent",
      "quote": "a gold-medal score on questions from the International Mathematical Olympiad"
    },
    {
      "kind": "press release",
      "citation": "Google DeepMind (2025). Advanced version of Gemini with Deep Think officially achieves gold-medal standard at the International Mathematical Olympiad. Google DeepMind blog.",
      "title": "Advanced version of Gemini with Deep Think officially achieves gold-medal standard at the International Mathematical Olympiad",
      "url": "https://deepmind.google/discover/blog/advanced-version-of-gemini-with-deep-think-officially-achieves-gold-medal-standard-at-the-international-mathematical-olympiad/",
      "date": "2025-07-21",
      "written_by": "makers",
      "quote": "We can confirm that Google DeepMind has reached the much-desired milestone, earning 35 out of a possible 42 points — a gold medal score."
    }
  ],
  "replication": {
    "produced_by": [
      "Manual translation of the 2024 problem statements into Lean",
      "AlphaProof reinforcement-learning proof search and AlphaGeometry 2 for the geometry problem",
      "Grading under IMO rules by two former IMO gold medalists"
    ],
    "must_hold": [
      "Each proof is machine-checked in Lean or graded by qualified IMO graders",
      "Problems are unseen by the system before the contest",
      "Grading criteria identical to those for human contestants"
    ],
    "echoes": [
      {
        "date": "2025-07-21",
        "setting": "IMO 2025; advanced Gemini Deep Think working end-to-end in natural language within the 4.5-hour limit; 35/42 graded and certified by IMO coordinators per DeepMind, confirmed by IMO president Gregor Dolinar",
        "model_version": "Gemini Deep Think (advanced version)",
        "outcome": "recurred",
        "source": "https://deepmind.google/discover/blog/advanced-version-of-gemini-with-deep-think-officially-achieves-gold-medal-standard-at-the-international-mathematical-olympiad/ ; https://www.nature.com/articles/d41586-025-02343-x"
      }
    ]
  },
  "paired_incident": null,
  "headline": "AlphaProof and AlphaGeometry 2 reach IMO silver-medal standard",
  "metric": "awarded 28 of 42 points, a silver-medal score",
  "comparator": null,
  "later": {
    "status": "persisted",
    "date": "2025-07-21",
    "note": "A year later DeepMind's successor system, an advanced version of Gemini Deep Think, scored 35 of 42 at IMO 2025 within the time limit, which the IMO president confirmed as a gold-medal score.",
    "quote": "We can confirm that Google DeepMind has reached the much-desired milestone, earning 35 out of a possible 42 points — a gold medal score.",
    "url": "https://deepmind.google/discover/blog/advanced-version-of-gemini-with-deep-think-officially-achieves-gold-medal-standard-at-the-international-mathematical-olympiad/"
  },
  "value": null,
  "developer_country": "United Kingdom",
  "deployer_country": "United Kingdom",
  "unrated_because": null,
  "brief_notes": null,
  "brief": null,
  "revisions": [
    {
      "date": "2026-10-20",
      "change": "Record drafted from the cited sources.",
      "source": null,
      "editor": "AIBD"
    },
    {
      "date": "2026-10-20",
      "change": "Category changed from 1 to 3 with both depths set to null and the taxonomy note rewritten, because the sources describe a research evaluation on IMO 2024 problems with no deployment and no identifiable beneficiary; the MIT Technology Review title and citation now carry the published headline's word “new”; the AI-role statement now says that grader Myers chaired the IMO 2024 Problem Selection Committee and that the 2024 result, unlike the 2025 one, was not officially certified by the IMO.",
      "source": "https://deepmind.google/discover/blog/ai-solves-imo-problems-at-silver-medal-level/ ; https://www.technologyreview.com/2024/07/25/1095315/google-deepminds-ai-systems-can-now-solve-complex-math-problems/ ; https://deepmind.google/discover/blog/advanced-version-of-gemini-with-deep-think-officially-achieves-gold-medal-standard-at-the-international-mathematical-olympiad/",
      "editor": "AIBD"
    },
    {
      "date": "2026-10-21",
      "change": "Added what happened since from the cited sources.",
      "source": "https://deepmind.google/discover/blog/advanced-version-of-gemini-with-deep-think-officially-achieves-gold-medal-standard-at-the-international-mathematical-olympiad/",
      "editor": "AIBD"
    },
    {
      "date": "2026-10-21",
      "change": "Benefit type set to Improved Task Accuracy under Trustible's full taxonomy of 23 types; it was Improved Knowledge Discovery among the six first used.",
      "source": "https://trustible.ai/post/a-framework-for-measuring-the-benefits-of-ai/",
      "editor": "AIBD"
    },
    {
      "date": "2026-10-21",
      "change": "Country of the developer and the deployer added from the organization's own site or a registry.",
      "source": "https://en.wikipedia.org/wiki/Google_DeepMind; https://en.wikipedia.org/wiki/Google_DeepMind",
      "editor": "AIBD"
    },
    {
      "date": "2026-10-21",
      "change": "Prose pass: a rating reason, account, the replication conditions, the system's part rewritten in shorter sentences with abbreviations expanded; facts, figures and quotations unchanged.",
      "source": null,
      "editor": "AIBD"
    },
    {
      "date": "2026-10-22",
      "change": "Organization name standardized to DeepMind.",
      "source": null,
      "editor": "AIBD"
    }
  ],
  "confidence": "reported",
  "shade": "medium",
  "claim_status": "Independently reported",
  "claim_basis": "Sources: four independent news reports and two press releases from the makers. The cited evidence includes no independent study or report and no finding by a regulator or court.",
  "profile": {
    "case_id": "AIBD-0070",
    "catalog_version": "1.0.0",
    "source_fingerprint": "4b78415afdaf96f4a254376344d86945bbf8cf56e8ae0cd1df787a64420515eb",
    "collection_refs": [
      {
        "collection_id": "aibd",
        "version": "snapshot-8bf7cfec9cb185aa"
      },
      {
        "collection_id": "aibd",
        "version": "2026-10-25"
      }
    ],
    "source_ids": [
      "AIBD-0070-source-0001",
      "AIBD-0070-source-0002",
      "AIBD-0070-source-0003",
      "AIBD-0070-source-0004",
      "AIBD-0070-source-0005",
      "AIBD-0070-source-0006"
    ],
    "families": {
      "strategic assessments": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "record_ids": []
      },
      "evaluations": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "record_ids": []
      },
      "monetary observations": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "record_ids": []
      },
      "institutional decisions": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "record_ids": []
      }
    },
    "fields": {
      "actors[]": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "developer": "DeepMind",
            "deployer": "DeepMind"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "developer",
            "deployer"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "actors[].ownership_control": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "ai_contribution": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "ai_role": {
              "status": "assessed",
              "statement": "The AI systems produced the proofs. Humans manually formalized the 2024 problem statements into Lean (Scientific American) and graded the output. In 2024 the solutions were graded by two mathematicians at DeepMind's request (one of them, Myers, chaired the IMO 2024 Problem Selection Committee). The result was not officially certified by the IMO. DeepMind states the 2025 result was graded and certified by IMO coordinators, with the IMO president's confirmation appearing in the vendor blog. The cited sources do not state whether OpenAI's 2025 claim was certified by the IMO."
            }
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "ai_role"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "ai_relationship": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "category": "general benefit",
            "ai_role": {
              "status": "assessed",
              "statement": "The AI systems produced the proofs. Humans manually formalized the 2024 problem statements into Lean (Scientific American) and graded the output. In 2024 the solutions were graded by two mathematicians at DeepMind's request (one of them, Myers, chaired the IMO 2024 Problem Selection Committee). The result was not officially certified by the IMO. DeepMind states the 2025 result was graded and certified by IMO coordinators, with the IMO president's confirmation appearing in the vendor blog. The cited sources do not state whether OpenAI's 2025 claim was certified by the IMO."
            }
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "ai_role",
            "category"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "assessments[].alternatives": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "assessments[].assessor_date": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "assessments[].depth": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "assessments[].display_confidence": {
        "state": "value_present",
        "value": {
          "kind": "structured",
          "data": {
            "confidence": "medium",
            "evidence_word": "reported",
            "claim_status": "Independently reported",
            "basis": "Sources: four independent news reports and two press releases from the makers. The cited evidence includes no independent study or report and no finding by a regulator or court.",
            "interpretation": "Existing display rule preserved; the richer outcome-specific confidence question still needs review."
          }
        },
        "provenance": {
          "kind": "curatorial",
          "basis": "Derived from the existing case display properties; not a new evidentiary judgment.",
          "record_fields": [],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "assessments[].rationale": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "ratings": [
              {
                "group": "organizational",
                "reason": "A capability evaluation on IMO 2024 problems for the developer and the IMO community. The sources describe grading and scores, not a deployment or an observed organizational change."
              },
              {
                "group": "societal",
                "reason": "Proofs of already-solved contest problems graded correct, with no identifiable beneficiary beyond the research community. Scientific American notes around 60 students scored better in 2024."
              }
            ]
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "ratings"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "assessments[].rubric_version": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "assessments[].status_basis": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "assessments[].target": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "ratings": [
              {
                "group": "organizational",
                "reason": "A capability evaluation on IMO 2024 problems for the developer and the IMO community. The sources describe grading and scores, not a deployment or an observed organizational change."
              },
              {
                "group": "societal",
                "reason": "Proofs of already-solved contest problems graded correct, with no identifiable beneficiary beyond the research community. Scientific American notes around 60 students scored better in 2024."
              }
            ]
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "ratings"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "availability": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "brief": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "case_kind": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "case_links[]": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "claims[].evidence_links": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "claims[].evidence_strength": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "claims[].missingness": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "claims[].proposition": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "cross_border_flows[]": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "decisions[].action_outcome": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "institutional decisions"
      },
      "decisions[].grounds": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "institutional decisions"
      },
      "decisions[].institution_task": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "institutional decisions"
      },
      "decisions[].success_criterion": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "institutional decisions"
      },
      "deployment_stage": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "economics[].amount": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "economics[].costs[]": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "economics[].counterfactual": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "economics[].currency_price_basis": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "economics[].gross_net": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "economics[].measure_type": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "economics[].period_unit": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "economics[].realization": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "economics[].recipient_payer": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "economics[].return_payback": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "economics[].valuation_method": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "evaluations[].ai_uplift": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations"
      },
      "evaluations[].comparator": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations"
      },
      "evaluations[].design": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations"
      },
      "evaluations[].effect": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations"
      },
      "evaluations[].exposure": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations"
      },
      "evaluations[].id": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations"
      },
      "evaluations[].measurement_method": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations"
      },
      "evaluations[].metric": {
        "state": "not_assessed",
        "provenance": {
          "kind": "legacy_record",
          "basis": "Mapped from the existing case description without a new external source review.",
          "record_fields": [
            "metric"
          ],
          "source_refs": []
        },
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations",
        "display": {
          "answer": "awarded 28 of 42 points, a silver-medal score",
          "editor_note": ""
        }
      },
      "evaluations[].reproduction_materials": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations"
      },
      "evaluations[].setting_sample": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations"
      },
      "evaluations[].uncertainty_limitations": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations"
      },
      "external_references[]": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "follow_up[]": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "later": {
              "status": "persisted",
              "date": "2025-07-21",
              "note": "A year later DeepMind's successor system, an advanced version of Gemini Deep Think, scored 35 of 42 at IMO 2025 within the time limit, which the IMO president confirmed as a gold-medal score.",
              "quote": "We can confirm that Google DeepMind has reached the much-desired milestone, earning 35 out of a possible 42 points — a gold medal score.",
              "url": "https://deepmind.google/discover/blog/advanced-version-of-gemini-with-deep-think-officially-achieves-gold-medal-standard-at-the-international-mathematical-olympiad/"
            }
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "later"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "human_oversight": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "id": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "id": "AIBD-0070"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "id"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "infrastructure_dependencies[]": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "outcomes[].beneficiaries": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "outcomes[].beneficiary_count": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "outcomes[].benefit_type": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "benefit_type": "Improved Task Accuracy",
            "taxonomy_note": "A graded competition score is read as task performance; no deployment or user is involved."
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "benefit_type",
            "taxonomy_note"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "outcomes[].claim": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "account": "Google DeepMind's AlphaProof (reinforcement learning over the Lean proof language) and AlphaGeometry 2 produced solutions to four of the six 2024 International Mathematical Olympiad problems. Because the systems work in formal language, the problems were first translated manually into Lean. One problem was solved within minutes and others took up to three days, longer than the contest allows. Two former IMO gold medalists, Sir Timothy Gowers and Joseph Myers, graded the solutions under IMO rules. They awarded 28 of 42 points, a silver-medal score. DeepMind announced the result on 25 July 2024 (grading date not given). In July 2025 a Gemini Deep Think model working in natural language within the time limit scored 35 of 42. IMO president Gregor Dolinar confirmed this as a gold-medal score. Nature reported that OpenAI also claimed a gold-level result.",
            "benefit_type": "Improved Task Accuracy"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "account",
            "benefit_type"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "outcomes[].distribution": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "outcomes[].duration": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "outcomes[].id": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "outcomes[].stakeholder_group": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "ratings": [
              {
                "group": "organizational",
                "reason": "A capability evaluation on IMO 2024 problems for the developer and the IMO community. The sources describe grading and scores, not a deployment or an observed organizational change."
              },
              {
                "group": "societal",
                "reason": "Proofs of already-solved contest problems graded correct, with no identifiable beneficiary beyond the research community. Scientific American notes around 60 students scored better in 2024."
              }
            ]
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "ratings"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "outcomes[].status": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "outcomes[].tradeoffs": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "outcomes[].unexpected": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "unexpected": false,
            "purpose": "Solve competition mathematics problems with machine-checkable formal proofs"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "unexpected",
            "purpose"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "places[]": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "developer_country": "United Kingdom",
            "deployer_country": "United Kingdom"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "developer_country",
            "deployer_country"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "purpose": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "purpose": "Solve competition mathematics problems with machine-checkable formal proofs"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "purpose"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "record_dates": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "date_observed": "2024-07-25",
            "revisions": [
              {
                "date": "2026-10-20",
                "change": "Record drafted from the cited sources.",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-20",
                "change": "Category changed from 1 to 3 with both depths set to null and the taxonomy note rewritten, because the sources describe a research evaluation on IMO 2024 problems with no deployment and no identifiable beneficiary; the MIT Technology Review title and citation now carry the published headline's word “new”; the AI-role statement now says that grader Myers chaired the IMO 2024 Problem Selection Committee and that the 2024 result, unlike the 2025 one, was not officially certified by the IMO.",
                "source": "https://deepmind.google/discover/blog/ai-solves-imo-problems-at-silver-medal-level/ ; https://www.technologyreview.com/2024/07/25/1095315/google-deepminds-ai-systems-can-now-solve-complex-math-problems/ ; https://deepmind.google/discover/blog/advanced-version-of-gemini-with-deep-think-officially-achieves-gold-medal-standard-at-the-international-mathematical-olympiad/",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-21",
                "change": "Added what happened since from the cited sources.",
                "source": "https://deepmind.google/discover/blog/advanced-version-of-gemini-with-deep-think-officially-achieves-gold-medal-standard-at-the-international-mathematical-olympiad/",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-21",
                "change": "Benefit type set to Improved Task Accuracy under Trustible's full taxonomy of 23 types; it was Improved Knowledge Discovery among the six first used.",
                "source": "https://trustible.ai/post/a-framework-for-measuring-the-benefits-of-ai/",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-21",
                "change": "Country of the developer and the deployer added from the organization's own site or a registry.",
                "source": "https://en.wikipedia.org/wiki/Google_DeepMind; https://en.wikipedia.org/wiki/Google_DeepMind",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-21",
                "change": "Prose pass: a rating reason, account, the replication conditions, the system's part rewritten in shorter sentences with abbreviations expanded; facts, figures and quotations unchanged.",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-22",
                "change": "Organization name standardized to DeepMind.",
                "editor": "AIBD"
              }
            ]
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "date_observed",
            "revisions"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "replication.attempts[]": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "replication": {
              "produced_by": [
                "Manual translation of the 2024 problem statements into Lean",
                "AlphaProof reinforcement-learning proof search and AlphaGeometry 2 for the geometry problem",
                "Grading under IMO rules by two former IMO gold medalists"
              ],
              "must_hold": [
                "Each proof is machine-checked in Lean or graded by qualified IMO graders",
                "Problems are unseen by the system before the contest",
                "Grading criteria identical to those for human contestants"
              ],
              "echoes": [
                {
                  "date": "2025-07-21",
                  "setting": "IMO 2025; advanced Gemini Deep Think working end-to-end in natural language within the 4.5-hour limit; 35/42 graded and certified by IMO coordinators per DeepMind, confirmed by IMO president Gregor Dolinar",
                  "model_version": "Gemini Deep Think (advanced version)",
                  "outcome": "recurred",
                  "source": "https://deepmind.google/discover/blog/advanced-version-of-gemini-with-deep-think-officially-achieves-gold-medal-standard-at-the-international-mathematical-olympiad/ ; https://www.nature.com/articles/d41586-025-02343-x"
                }
              ]
            }
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "replication"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "replication.conditions": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "replication": {
              "produced_by": [
                "Manual translation of the 2024 problem statements into Lean",
                "AlphaProof reinforcement-learning proof search and AlphaGeometry 2 for the geometry problem",
                "Grading under IMO rules by two former IMO gold medalists"
              ],
              "must_hold": [
                "Each proof is machine-checked in Lean or graded by qualified IMO graders",
                "Problems are unseen by the system before the contest",
                "Grading criteria identical to those for human contestants"
              ],
              "echoes": [
                {
                  "date": "2025-07-21",
                  "setting": "IMO 2025; advanced Gemini Deep Think working end-to-end in natural language within the 4.5-hour limit; 35/42 graded and certified by IMO coordinators per DeepMind, confirmed by IMO president Gregor Dolinar",
                  "model_version": "Gemini Deep Think (advanced version)",
                  "outcome": "recurred",
                  "source": "https://deepmind.google/discover/blog/advanced-version-of-gemini-with-deep-think-officially-achieves-gold-medal-standard-at-the-international-mathematical-olympiad/ ; https://www.nature.com/articles/d41586-025-02343-x"
                }
              ]
            }
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "replication"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "revision_history[]": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "revisions": [
              {
                "date": "2026-10-20",
                "change": "Record drafted from the cited sources.",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-20",
                "change": "Category changed from 1 to 3 with both depths set to null and the taxonomy note rewritten, because the sources describe a research evaluation on IMO 2024 problems with no deployment and no identifiable beneficiary; the MIT Technology Review title and citation now carry the published headline's word “new”; the AI-role statement now says that grader Myers chaired the IMO 2024 Problem Selection Committee and that the 2024 result, unlike the 2025 one, was not officially certified by the IMO.",
                "source": "https://deepmind.google/discover/blog/ai-solves-imo-problems-at-silver-medal-level/ ; https://www.technologyreview.com/2024/07/25/1095315/google-deepminds-ai-systems-can-now-solve-complex-math-problems/ ; https://deepmind.google/discover/blog/advanced-version-of-gemini-with-deep-think-officially-achieves-gold-medal-standard-at-the-international-mathematical-olympiad/",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-21",
                "change": "Added what happened since from the cited sources.",
                "source": "https://deepmind.google/discover/blog/advanced-version-of-gemini-with-deep-think-officially-achieves-gold-medal-standard-at-the-international-mathematical-olympiad/",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-21",
                "change": "Benefit type set to Improved Task Accuracy under Trustible's full taxonomy of 23 types; it was Improved Knowledge Discovery among the six first used.",
                "source": "https://trustible.ai/post/a-framework-for-measuring-the-benefits-of-ai/",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-21",
                "change": "Country of the developer and the deployer added from the organization's own site or a registry.",
                "source": "https://en.wikipedia.org/wiki/Google_DeepMind; https://en.wikipedia.org/wiki/Google_DeepMind",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-21",
                "change": "Prose pass: a rating reason, account, the replication conditions, the system's part rewritten in shorter sentences with abbreviations expanded; facts, figures and quotations unchanged.",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-22",
                "change": "Organization name standardized to DeepMind.",
                "editor": "AIBD"
              }
            ]
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "revisions"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "sector": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "domain": "Mathematics competitions",
            "segment": "Olympiad mathematics"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "domain",
            "segment"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "sources[].access_version": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "sources[].citation_locator": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "evidence": [
              {
                "kind": "news report",
                "citation": "Bischoff, M. (2024). AI Reaches Silver-Medal Level at This Year's Math Olympiad. Scientific American.",
                "title": "AI Reaches Silver-Medal Level at This Year's Math Olympiad",
                "url": "https://www.scientificamerican.com/article/ai-reaches-silver-medal-level-at-this-years-math-olympiad/",
                "date": "2024-08-06",
                "written_by": "independent",
                "quote": "Gowers and mathematician Joseph K. Myers, another previous gold medalist, evaluated the solutions of the two AI systems using the same criteria as was used for the human participants."
              },
              {
                "kind": "news report",
                "citation": "Williams, R. (2024). Google DeepMind's new AI systems can now solve complex math problems. MIT Technology Review.",
                "title": "Google DeepMind's new AI systems can now solve complex math problems",
                "url": "https://www.technologyreview.com/2024/07/25/1095315/google-deepminds-ai-systems-can-now-solve-complex-math-problems/",
                "date": "2024-07-25",
                "written_by": "independent",
                "quote": "They awarded each of their four correct answers full marks (seven out of seven), giving the systems a total of 28 points out of a maximum of 42."
              },
              {
                "kind": "news report",
                "citation": "Castelvecchi, D. (2024). DeepMind hits milestone in solving maths problems — AI's next grand challenge. Nature.",
                "title": "DeepMind hits milestone in solving maths problems — AI's next grand challenge",
                "url": "https://www.nature.com/articles/d41586-024-02441-2",
                "date": "2024-07-25",
                "written_by": "independent",
                "quote": "AlphaProof showed its prowess on questions from this year's Mathematical Olympiad — a step in the race to create substantial proofs with artificial intelligence."
              },
              {
                "kind": "press release",
                "citation": "Google DeepMind (2024). AI achieves silver-medal standard solving International Mathematical Olympiad problems. Google DeepMind blog.",
                "title": "AI achieves silver-medal standard solving International Mathematical Olympiad problems",
                "url": "https://deepmind.google/discover/blog/ai-solves-imo-problems-at-silver-medal-level/",
                "date": "2024-07-25",
                "written_by": "makers",
                "quote": "Our system achieved a final score of 28 points, earning a perfect score on each problem solved"
              },
              {
                "kind": "news report",
                "citation": "Castelvecchi, D. (2025). DeepMind and OpenAI models solve maths problems at level of top students. Nature.",
                "title": "DeepMind and OpenAI models solve maths problems at level of top students",
                "url": "https://www.nature.com/articles/d41586-025-02343-x",
                "date": "2025-07-24",
                "written_by": "independent",
                "quote": "a gold-medal score on questions from the International Mathematical Olympiad"
              },
              {
                "kind": "press release",
                "citation": "Google DeepMind (2025). Advanced version of Gemini with Deep Think officially achieves gold-medal standard at the International Mathematical Olympiad. Google DeepMind blog.",
                "title": "Advanced version of Gemini with Deep Think officially achieves gold-medal standard at the International Mathematical Olympiad",
                "url": "https://deepmind.google/discover/blog/advanced-version-of-gemini-with-deep-think-officially-achieves-gold-medal-standard-at-the-international-mathematical-olympiad/",
                "date": "2025-07-21",
                "written_by": "makers",
                "quote": "We can confirm that Google DeepMind has reached the much-desired milestone, earning 35 out of a possible 42 points — a gold medal score."
              }
            ]
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "evidence"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "sources[].id": {
        "state": "value_present",
        "value": {
          "kind": "identifiers",
          "identifiers": [
            "AIBD-0070-source-0001",
            "AIBD-0070-source-0002",
            "AIBD-0070-source-0003",
            "AIBD-0070-source-0004",
            "AIBD-0070-source-0005",
            "AIBD-0070-source-0006"
          ],
          "role": "Existing evidence items, in their original order"
        },
        "provenance": {
          "kind": "curatorial",
          "basis": "Stable within the fingerprinted record version; no source content or source review has been added.",
          "record_fields": [],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "complete"
      },
      "sources[].language": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "sources[].relationship": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "evidence": [
              {
                "kind": "news report",
                "citation": "Bischoff, M. (2024). AI Reaches Silver-Medal Level at This Year's Math Olympiad. Scientific American.",
                "title": "AI Reaches Silver-Medal Level at This Year's Math Olympiad",
                "url": "https://www.scientificamerican.com/article/ai-reaches-silver-medal-level-at-this-years-math-olympiad/",
                "date": "2024-08-06",
                "written_by": "independent",
                "quote": "Gowers and mathematician Joseph K. Myers, another previous gold medalist, evaluated the solutions of the two AI systems using the same criteria as was used for the human participants."
              },
              {
                "kind": "news report",
                "citation": "Williams, R. (2024). Google DeepMind's new AI systems can now solve complex math problems. MIT Technology Review.",
                "title": "Google DeepMind's new AI systems can now solve complex math problems",
                "url": "https://www.technologyreview.com/2024/07/25/1095315/google-deepminds-ai-systems-can-now-solve-complex-math-problems/",
                "date": "2024-07-25",
                "written_by": "independent",
                "quote": "They awarded each of their four correct answers full marks (seven out of seven), giving the systems a total of 28 points out of a maximum of 42."
              },
              {
                "kind": "news report",
                "citation": "Castelvecchi, D. (2024). DeepMind hits milestone in solving maths problems — AI's next grand challenge. Nature.",
                "title": "DeepMind hits milestone in solving maths problems — AI's next grand challenge",
                "url": "https://www.nature.com/articles/d41586-024-02441-2",
                "date": "2024-07-25",
                "written_by": "independent",
                "quote": "AlphaProof showed its prowess on questions from this year's Mathematical Olympiad — a step in the race to create substantial proofs with artificial intelligence."
              },
              {
                "kind": "press release",
                "citation": "Google DeepMind (2024). AI achieves silver-medal standard solving International Mathematical Olympiad problems. Google DeepMind blog.",
                "title": "AI achieves silver-medal standard solving International Mathematical Olympiad problems",
                "url": "https://deepmind.google/discover/blog/ai-solves-imo-problems-at-silver-medal-level/",
                "date": "2024-07-25",
                "written_by": "makers",
                "quote": "Our system achieved a final score of 28 points, earning a perfect score on each problem solved"
              },
              {
                "kind": "news report",
                "citation": "Castelvecchi, D. (2025). DeepMind and OpenAI models solve maths problems at level of top students. Nature.",
                "title": "DeepMind and OpenAI models solve maths problems at level of top students",
                "url": "https://www.nature.com/articles/d41586-025-02343-x",
                "date": "2025-07-24",
                "written_by": "independent",
                "quote": "a gold-medal score on questions from the International Mathematical Olympiad"
              },
              {
                "kind": "press release",
                "citation": "Google DeepMind (2025). Advanced version of Gemini with Deep Think officially achieves gold-medal standard at the International Mathematical Olympiad. Google DeepMind blog.",
                "title": "Advanced version of Gemini with Deep Think officially achieves gold-medal standard at the International Mathematical Olympiad",
                "url": "https://deepmind.google/discover/blog/advanced-version-of-gemini-with-deep-think-officially-achieves-gold-medal-standard-at-the-international-mathematical-olympiad/",
                "date": "2025-07-21",
                "written_by": "makers",
                "quote": "We can confirm that Google DeepMind has reached the much-desired milestone, earning 35 out of a possible 42 points — a gold medal score."
              }
            ]
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "evidence"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "sources[].upstream_sources": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "strategic_assessments[]": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "strategic assessments"
      },
      "summary": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "summary": "DeepMind AI scored 28/42 on IMO 2024 problems, graded by Gowers and Myers; Gemini Deep Think's 35/42 in 2025 was IMO-certified gold",
            "account": "Google DeepMind's AlphaProof (reinforcement learning over the Lean proof language) and AlphaGeometry 2 produced solutions to four of the six 2024 International Mathematical Olympiad problems. Because the systems work in formal language, the problems were first translated manually into Lean. One problem was solved within minutes and others took up to three days, longer than the contest allows. Two former IMO gold medalists, Sir Timothy Gowers and Joseph Myers, graded the solutions under IMO rules. They awarded 28 of 42 points, a silver-medal score. DeepMind announced the result on 25 July 2024 (grading date not given). In July 2025 a Gemini Deep Think model working in natural language within the time limit scored 35 of 42. IMO president Gregor Dolinar confirmed this as a gold-medal score. Nature reported that OpenAI also claimed a gold-level result."
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "summary",
            "account"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "systems[].autonomy_permissions": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "systems[].component_role": {
        "state": "value_present",
        "value": {
          "kind": "text",
          "text": "The systems generated mathematical proofs."
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Restated the mechanical task already described in the existing system and AI-role fields. No new source review is claimed.",
          "record_fields": [
            "system",
            "ai_role"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "systems[].deployment_configuration": {
        "state": "value_present",
        "value": {
          "kind": "text",
          "text": "The 2024 work combined AlphaProof and AlphaGeometry 2. A later report concerned Gemini Deep Think."
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Separated the model, software, hardware, or operation already described in the existing record. No new source review is claimed.",
          "record_fields": [
            "model_version",
            "system",
            "ai_role"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "systems[].inputs_outputs": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "systems[].model_name": {
        "state": "value_present",
        "value": {
          "kind": "text",
          "text": "AlphaProof and AlphaGeometry 2 in the 2024 work."
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Separated the model, software, hardware, or operation already described in the existing record. No new source review is claimed.",
          "record_fields": [
            "model_version",
            "system",
            "ai_role"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "systems[].model_version": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "model_version": "AlphaProof (2024) and AlphaGeometry 2; 2025 echo: advanced Gemini Deep Think"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "model_version"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial",
        "display": {
          "answer": "Exact release not established.",
          "editor_note": ""
        }
      },
      "systems[].product_name": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "system": "AlphaProof and AlphaGeometry 2"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "system"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "systems[].provider": {
        "state": "value_present",
        "value": {
          "kind": "structured",
          "data": {
            "application_developer": "DeepMind"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Mapped from the existing case description without a new external source review.",
          "record_fields": [
            "developer"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "taxonomy_crosswalks[]": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "title": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "title": "AlphaProof and AlphaGeometry 2 reach silver-medal standard on IMO 2024 problems, graded by two IMO gold medallists; IMO-certified gold follows in 2025",
            "headline": "AlphaProof and AlphaGeometry 2 reach IMO silver-medal standard"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "title",
            "headline"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "version": {
        "state": "value_present",
        "value": {
          "kind": "identifiers",
          "identifiers": [
            "4b78415afdaf96f4a254376344d86945bbf8cf56e8ae0cd1df787a64420515eb"
          ],
          "role": "SHA-256 of normalized original case data"
        },
        "provenance": {
          "kind": "curatorial",
          "basis": "Deterministic content version assigned by the local migration.",
          "record_fields": [],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "complete"
      },
      "workflow": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "account": "Google DeepMind's AlphaProof (reinforcement learning over the Lean proof language) and AlphaGeometry 2 produced solutions to four of the six 2024 International Mathematical Olympiad problems. Because the systems work in formal language, the problems were first translated manually into Lean. One problem was solved within minutes and others took up to three days, longer than the contest allows. Two former IMO gold medalists, Sir Timothy Gowers and Joseph Myers, graded the solutions under IMO rules. They awarded 28 of 42 points, a silver-medal score. DeepMind announced the result on 25 July 2024 (grading date not given). In July 2025 a Gemini Deep Think model working in natural language within the time limit scored 35 of 42. IMO president Gregor Dolinar confirmed this as a gold-medal score. Nature reported that OpenAI also claimed a gold-level result.",
            "replication": {
              "produced_by": [
                "Manual translation of the 2024 problem statements into Lean",
                "AlphaProof reinforcement-learning proof search and AlphaGeometry 2 for the geometry problem",
                "Grading under IMO rules by two former IMO gold medalists"
              ],
              "must_hold": [
                "Each proof is machine-checked in Lean or graded by qualified IMO graders",
                "Problems are unseen by the system before the contest",
                "Grading criteria identical to those for human contestants"
              ],
              "echoes": [
                {
                  "date": "2025-07-21",
                  "setting": "IMO 2025; advanced Gemini Deep Think working end-to-end in natural language within the 4.5-hour limit; 35/42 graded and certified by IMO coordinators per DeepMind, confirmed by IMO president Gregor Dolinar",
                  "model_version": "Gemini Deep Think (advanced version)",
                  "outcome": "recurred",
                  "source": "https://deepmind.google/discover/blog/advanced-version-of-gemini-with-deep-think-officially-achieves-gold-medal-standard-at-the-international-mathematical-olympiad/ ; https://www.nature.com/articles/d41586-025-02343-x"
                }
              ]
            }
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "account",
            "replication"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      }
    },
    "summary": {
      "total": 91,
      "addressed": 91,
      "known": 32,
      "reviewed": 0,
      "record_mapped": 32,
      "not_assessed": 59,
      "complete": false,
      "by_state": {
        "value_present": 32,
        "not_reported": 0,
        "unresolved": 0,
        "not_assessed": 59,
        "not_applicable": 0,
        "withheld": 0,
        "source_unavailable": 0
      }
    }
  }
}