{
  "id": "AIBD-0238",
  "title": "DARPA's AIxCC final: autonomous systems find 54 of 63 synthetic vulnerabilities, patch 43, and surface 18 real bugs in open-source code",
  "summary": "At DEF CON 33 (8 August 2025) DARPA reported seven teams' systems found 54 synthetic vulnerabilities, patched 43, and found 18 real bugs for disclosure; Team Atlanta won $4 million.",
  "date_observed": "2025-08-08",
  "date_basis": "unassessed",
  "date_precision": "unassessed",
  "benefit_status": null,
  "source_collection": null,
  "source_entry": null,
  "account": "DARPA's results release describes the Final Competition. Teams' cyber reasoning systems tried to find and patch synthetic vulnerabilities across 54 million lines of real-world open-source code. They found 54 unique synthetic vulnerabilities in 63 challenges and patched 43. They also found 18 real, non-synthetic vulnerabilities (six in C codebases, 12 in Java), now being responsibly disclosed. There were 11 patches for real bugs. The average cost was about $152 per task. Team Atlanta (Georgia Tech, Samsung Research, KAIST, POSTECH) won $4 million, Trail of Bits $3 million and Theori $1.5 million. Four of seven systems were released open source. The Record reported the same figures from Las Vegas with program manager Andrew Carney's remarks. curl maintainer Daniel Stenberg, whose project was among the targets, examined the injected curl flaws. He judged them straightforward and not deeply hidden.",
  "category": "general benefit",
  "unexpected": false,
  "purpose": "Autonomous AI systems that find and patch vulnerabilities in open-source software underlying critical infrastructure.",
  "system": "AIxCC finalist cyber reasoning systems (Team Atlanta, Trail of Bits, Theori and four others)",
  "model_version": null,
  "developer": "Seven finalist teams (Team Atlanta et al.), using LLM credits from Anthropic, Google and OpenAI",
  "deployer": "DARPA (with ARPA-H), AIxCC Final Competition",
  "location": "Las Vegas, United States",
  "domain": "Cybersecurity / automated vulnerability discovery and patching",
  "segment": "Government",
  "benefit_type": "Reduced Risk",
  "taxonomy_note": "A competition result; the real bugs found are read as risk reduced.",
  "registry_ids": {},
  "ratings": [
    {
      "group": "societal",
      "depth": null,
      "reason": "Aggregate competition results. No specific attack or deployment outcome documented."
    },
    {
      "group": "organizational",
      "depth": null,
      "reason": "Open-source maintainers received disclosures. No fix is individually documented in the sources."
    }
  ],
  "ai_role": {
    "status": "assessed",
    "statement": "DARPA, the organizer, reports the figures. The Record corroborates from the event. Stenberg's independent look at the curl tasks suggests the injected flaws were easy. That bounds how much the synthetic scores show."
  },
  "evidence": [
    {
      "kind": "press release",
      "citation": "DARPA, news release, 8 Aug 2025",
      "title": "AI Cyber Challenge marks pivotal inflection point for cyber defense",
      "url": "https://www.darpa.mil/news/2025/aixcc-results",
      "date": "2025-08-08",
      "written_by": "deployer",
      "quote": "In the Final Competition, teams also discovered 18 real, non-synthetic vulnerabilities that are being responsibly disclosed to open source project maintainers."
    },
    {
      "kind": "news report",
      "citation": "Jonathan Greig, The Record from Recorded Future News, 8 Aug 2025",
      "title": "DARPA announces $4 million winner of AI code review competition at DEF CON",
      "url": "https://therecord.media/darpa-ai-code-competition-winner-def-con",
      "date": "2025-08-08",
      "written_by": "independent",
      "quote": "Overall, competitors found 54 unique synthetic vulnerabilities and were able to patch 43 of them — representing 77% of the synthetic vulnerabilities introduced."
    },
    {
      "kind": "report",
      "citation": "Daniel Stenberg, daniel.haxx.se, 22 Oct 2025",
      "title": "AIxCC curl details",
      "url": "https://daniel.haxx.se/blog/2025/10/22/aixcc-curl-details/",
      "date": "2025-10-22",
      "written_by": "beneficiary",
      "quote": "As seen above here, they were all rather straight forward and not hidden or deeply layered very much."
    }
  ],
  "replication": {
    "produced_by": [
      "Injected flaws in real open-source projects with scoring for proofs and patches",
      "Two years of funded development and frontier-lab model credits"
    ],
    "must_hold": [
      "Real-world codebases with harder, layered flaws than the injected ones",
      "Maintainer acceptance of machine-generated patches"
    ],
    "echoes": []
  },
  "paired_incident": null,
  "headline": "AIxCC systems find 54 of 63 synthetic vulnerabilities, patch 43",
  "metric": "found 54 synthetic vulnerabilities, patched 43, and found 18 real bugs for disclosure",
  "comparator": {
    "against": "the same competition's semifinal round (2024)",
    "before": "37% at semifinals",
    "after": "teams identified 86% of the competition's synthetic vulnerabilities",
    "basis": "measured",
    "quote": "In the Final Competition scored round, teams identified 86% of the competition's synthetic vulnerabilities, an increase from 37% at semifinals, and patched 68% of the vulnerabilities identified, an increase from 25% at semifinals.",
    "url": "https://www.darpa.mil/news/2025/aixcc-results"
  },
  "later": {
    "status": "unknown",
    "date": null,
    "note": "The only later item found is curl maintainer Daniel Stenberg's 22 October 2025 review judging the injected curl flaws straightforward; no adoption, reversal or litigation was found.",
    "quote": null,
    "url": null
  },
  "value": {
    "amount": "$152",
    "what": "average cost per competition task for the systems' bug reports and patches, which DARPA calls a fraction of the cost of traditional methods",
    "who": "DARPA (cost of running the competitors' cyber reasoning systems per task)",
    "estimate": false,
    "quote": "Competitor CRSs proved they can create valuable bug reports and patches for a fraction of the cost of traditional methods, with an average cost per competition task of about $152.",
    "url": "https://www.darpa.mil/news/2025/aixcc-results"
  },
  "developer_country": null,
  "deployer_country": "United States",
  "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": "2026-10-21",
      "change": "Added what the benefit is measured against, the value as stated from the cited sources.",
      "source": "https://www.darpa.mil/news/2025/aixcc-results; https://www.darpa.mil/news/2025/aixcc-results",
      "editor": "AIBD"
    },
    {
      "date": "2026-10-21",
      "change": "Benefit type set to Reduced Risk 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 deployer added from the organization's own site or a registry.",
      "source": "https://en.wikipedia.org/wiki/DARPA",
      "editor": "AIBD"
    },
    {
      "date": "2026-10-21",
      "change": "Prose pass: a rating reason, account, the system's part rewritten in shorter sentences with abbreviations expanded; facts, figures and quotations unchanged.",
      "source": null,
      "editor": "AIBD"
    }
  ],
  "confidence": "reported",
  "shade": "medium",
  "claim_status": "Independently reported",
  "claim_basis": "Sources: one independent news report, the deployer's press release and the beneficiary's report. The cited evidence includes no independent study or report and no finding by a regulator or court.",
  "profile": {
    "case_id": "AIBD-0238",
    "catalog_version": "1.0.0",
    "source_fingerprint": "01edde86def16471a3fe4b3c89e5f67489b28fa09b20437cf77586aebe710a73",
    "collection_refs": [
      {
        "collection_id": "aibd",
        "version": "snapshot-8bf7cfec9cb185aa"
      },
      {
        "collection_id": "aibd",
        "version": "2026-10-25"
      },
      {
        "collection_id": "chanticleer",
        "version": "2026-10-25"
      }
    ],
    "source_ids": [
      "AIBD-0238-source-0001",
      "AIBD-0238-source-0002",
      "AIBD-0238-source-0003"
    ],
    "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": "value_present",
        "value": {
          "kind": "text",
          "text": "An existing source-stated monetary observation is present in the original value object."
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Existing value object only; its financial interpretation has not been reverified.",
          "record_fields": [
            "value"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial",
        "record_ids": [
          "AIBD-0238-legacy-value"
        ]
      },
      "institutional decisions": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "record_ids": []
      }
    },
    "fields": {
      "actors[]": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "developer": "Seven finalist teams (Team Atlanta et al.), using LLM credits from Anthropic, Google and OpenAI",
            "deployer": "DARPA (with ARPA-H), AIxCC Final Competition"
          }
        },
        "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": "DARPA, the organizer, reports the figures. The Record corroborates from the event. Stenberg's independent look at the curl tasks suggests the injected flaws were easy. That bounds how much the synthetic scores show."
            }
          }
        },
        "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": "DARPA, the organizer, reports the figures. The Record corroborates from the event. Stenberg's independent look at the curl tasks suggests the injected flaws were easy. That bounds how much the synthetic scores show."
            }
          }
        },
        "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: one independent news report, the deployer's press release and the beneficiary's report. 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": "societal",
                "reason": "Aggregate competition results. No specific attack or deployment outcome documented."
              },
              {
                "group": "organizational",
                "reason": "Open-source maintainers received disclosures. No fix is individually documented in the sources."
              }
            ]
          }
        },
        "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": "societal",
                "reason": "Aggregate competition results. No specific attack or deployment outcome documented."
              },
              {
                "group": "organizational",
                "reason": "Open-source maintainers received disclosures. No fix is individually documented in the sources."
              }
            ]
          }
        },
        "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": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "value": {
              "amount": "$152",
              "what": "average cost per competition task for the systems' bug reports and patches, which DARPA calls a fraction of the cost of traditional methods",
              "who": "DARPA (cost of running the competitors' cyber reasoning systems per task)",
              "estimate": false,
              "quote": "Competitor CRSs proved they can create valuable bug reports and patches for a fraction of the cost of traditional methods, with an average cost per competition task of about $152.",
              "url": "https://www.darpa.mil/news/2025/aixcc-results"
            }
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "value"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "economics[].costs[]": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "economics[].counterfactual": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "economics[].currency_price_basis": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "economics[].gross_net": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "economics[].measure_type": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "value": {
              "amount": "$152",
              "what": "average cost per competition task for the systems' bug reports and patches, which DARPA calls a fraction of the cost of traditional methods",
              "who": "DARPA (cost of running the competitors' cyber reasoning systems per task)",
              "estimate": false,
              "quote": "Competitor CRSs proved they can create valuable bug reports and patches for a fraction of the cost of traditional methods, with an average cost per competition task of about $152.",
              "url": "https://www.darpa.mil/news/2025/aixcc-results"
            }
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "value"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "economics[].period_unit": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "economics[].realization": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "economics[].recipient_payer": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "value": {
              "amount": "$152",
              "what": "average cost per competition task for the systems' bug reports and patches, which DARPA calls a fraction of the cost of traditional methods",
              "who": "DARPA (cost of running the competitors' cyber reasoning systems per task)",
              "estimate": false,
              "quote": "Competitor CRSs proved they can create valuable bug reports and patches for a fraction of the cost of traditional methods, with an average cost per competition task of about $152.",
              "url": "https://www.darpa.mil/news/2025/aixcc-results"
            }
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "value"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "economics[].return_payback": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "economics[].valuation_method": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "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": "found 54 synthetic vulnerabilities, patched 43, and found 18 real bugs for disclosure",
          "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": "unknown",
              "note": "The only later item found is curl maintainer Daniel Stenberg's 22 October 2025 review judging the injected curl flaws straightforward; no adoption, reversal or litigation was found."
            }
          }
        },
        "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-0238"
          }
        },
        "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": "Reduced Risk",
            "taxonomy_note": "A competition result; the real bugs found are read as risk reduced."
          }
        },
        "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": "DARPA's results release describes the Final Competition. Teams' cyber reasoning systems tried to find and patch synthetic vulnerabilities across 54 million lines of real-world open-source code. They found 54 unique synthetic vulnerabilities in 63 challenges and patched 43. They also found 18 real, non-synthetic vulnerabilities (six in C codebases, 12 in Java), now being responsibly disclosed. There were 11 patches for real bugs. The average cost was about $152 per task. Team Atlanta (Georgia Tech, Samsung Research, KAIST, POSTECH) won $4 million, Trail of Bits $3 million and Theori $1.5 million. Four of seven systems were released open source. The Record reported the same figures from Las Vegas with program manager Andrew Carney's remarks. curl maintainer Daniel Stenberg, whose project was among the targets, examined the injected curl flaws. He judged them straightforward and not deeply hidden.",
            "benefit_type": "Reduced Risk"
          }
        },
        "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": "societal",
                "reason": "Aggregate competition results. No specific attack or deployment outcome documented."
              },
              {
                "group": "organizational",
                "reason": "Open-source maintainers received disclosures. No fix is individually documented in the sources."
              }
            ]
          }
        },
        "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": "Autonomous AI systems that find and patch vulnerabilities in open-source software underlying critical infrastructure."
          }
        },
        "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": {
            "location": "Las Vegas, United States",
            "deployer_country": "United States"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "location",
            "deployer_country"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "purpose": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "purpose": "Autonomous AI systems that find and patch vulnerabilities in open-source software underlying critical infrastructure."
          }
        },
        "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": "2025-08-08",
            "revisions": [
              {
                "date": "2026-10-20",
                "change": "Record drafted from the cited sources.",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-21",
                "change": "Added what the benefit is measured against, the value as stated from the cited sources.",
                "source": "https://www.darpa.mil/news/2025/aixcc-results; https://www.darpa.mil/news/2025/aixcc-results",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-21",
                "change": "Benefit type set to Reduced Risk 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 deployer added from the organization's own site or a registry.",
                "source": "https://en.wikipedia.org/wiki/DARPA",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-21",
                "change": "Prose pass: a rating reason, account, the system's part rewritten in shorter sentences with abbreviations expanded; facts, figures and quotations unchanged.",
                "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": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "replication.conditions": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "replication": {
              "produced_by": [
                "Injected flaws in real open-source projects with scoring for proofs and patches",
                "Two years of funded development and frontier-lab model credits"
              ],
              "must_hold": [
                "Real-world codebases with harder, layered flaws than the injected ones",
                "Maintainer acceptance of machine-generated patches"
              ],
              "echoes": []
            }
          }
        },
        "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": "2026-10-21",
                "change": "Added what the benefit is measured against, the value as stated from the cited sources.",
                "source": "https://www.darpa.mil/news/2025/aixcc-results; https://www.darpa.mil/news/2025/aixcc-results",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-21",
                "change": "Benefit type set to Reduced Risk 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 deployer added from the organization's own site or a registry.",
                "source": "https://en.wikipedia.org/wiki/DARPA",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-21",
                "change": "Prose pass: a rating reason, account, the system's part rewritten in shorter sentences with abbreviations expanded; facts, figures and quotations unchanged.",
                "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": "Cybersecurity / automated vulnerability discovery and patching",
            "segment": "Government"
          }
        },
        "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": "press release",
                "citation": "DARPA, news release, 8 Aug 2025",
                "title": "AI Cyber Challenge marks pivotal inflection point for cyber defense",
                "url": "https://www.darpa.mil/news/2025/aixcc-results",
                "date": "2025-08-08",
                "written_by": "deployer",
                "quote": "In the Final Competition, teams also discovered 18 real, non-synthetic vulnerabilities that are being responsibly disclosed to open source project maintainers."
              },
              {
                "kind": "news report",
                "citation": "Jonathan Greig, The Record from Recorded Future News, 8 Aug 2025",
                "title": "DARPA announces $4 million winner of AI code review competition at DEF CON",
                "url": "https://therecord.media/darpa-ai-code-competition-winner-def-con",
                "date": "2025-08-08",
                "written_by": "independent",
                "quote": "Overall, competitors found 54 unique synthetic vulnerabilities and were able to patch 43 of them — representing 77% of the synthetic vulnerabilities introduced."
              },
              {
                "kind": "report",
                "citation": "Daniel Stenberg, daniel.haxx.se, 22 Oct 2025",
                "title": "AIxCC curl details",
                "url": "https://daniel.haxx.se/blog/2025/10/22/aixcc-curl-details/",
                "date": "2025-10-22",
                "written_by": "beneficiary",
                "quote": "As seen above here, they were all rather straight forward and not hidden or deeply layered very much."
              }
            ]
          }
        },
        "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-0238-source-0001",
            "AIBD-0238-source-0002",
            "AIBD-0238-source-0003"
          ],
          "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": "press release",
                "citation": "DARPA, news release, 8 Aug 2025",
                "title": "AI Cyber Challenge marks pivotal inflection point for cyber defense",
                "url": "https://www.darpa.mil/news/2025/aixcc-results",
                "date": "2025-08-08",
                "written_by": "deployer",
                "quote": "In the Final Competition, teams also discovered 18 real, non-synthetic vulnerabilities that are being responsibly disclosed to open source project maintainers."
              },
              {
                "kind": "news report",
                "citation": "Jonathan Greig, The Record from Recorded Future News, 8 Aug 2025",
                "title": "DARPA announces $4 million winner of AI code review competition at DEF CON",
                "url": "https://therecord.media/darpa-ai-code-competition-winner-def-con",
                "date": "2025-08-08",
                "written_by": "independent",
                "quote": "Overall, competitors found 54 unique synthetic vulnerabilities and were able to patch 43 of them — representing 77% of the synthetic vulnerabilities introduced."
              },
              {
                "kind": "report",
                "citation": "Daniel Stenberg, daniel.haxx.se, 22 Oct 2025",
                "title": "AIxCC curl details",
                "url": "https://daniel.haxx.se/blog/2025/10/22/aixcc-curl-details/",
                "date": "2025-10-22",
                "written_by": "beneficiary",
                "quote": "As seen above here, they were all rather straight forward and not hidden or deeply layered very much."
              }
            ]
          }
        },
        "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": "At DEF CON 33 (8 August 2025) DARPA reported seven teams' systems found 54 synthetic vulnerabilities, patched 43, and found 18 real bugs for disclosure; Team Atlanta won $4 million.",
            "account": "DARPA's results release describes the Final Competition. Teams' cyber reasoning systems tried to find and patch synthetic vulnerabilities across 54 million lines of real-world open-source code. They found 54 unique synthetic vulnerabilities in 63 challenges and patched 43. They also found 18 real, non-synthetic vulnerabilities (six in C codebases, 12 in Java), now being responsibly disclosed. There were 11 patches for real bugs. The average cost was about $152 per task. Team Atlanta (Georgia Tech, Samsung Research, KAIST, POSTECH) won $4 million, Trail of Bits $3 million and Theori $1.5 million. Four of seven systems were released open source. The Record reported the same figures from Las Vegas with program manager Andrew Carney's remarks. curl maintainer Daniel Stenberg, whose project was among the targets, examined the injected curl flaws. He judged them straightforward and not deeply hidden."
          }
        },
        "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": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "systems[].deployment_configuration": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "systems[].inputs_outputs": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "systems[].model_name": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "systems[].model_version": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "systems[].product_name": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "system": "AIxCC finalist cyber reasoning systems (Team Atlanta, Trail of Bits, Theori and four others)"
          }
        },
        "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": "Seven finalist teams (Team Atlanta et al.), using LLM credits from Anthropic, Google and OpenAI"
          }
        },
        "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": "DARPA's AIxCC final: autonomous systems find 54 of 63 synthetic vulnerabilities, patch 43, and surface 18 real bugs in open-source code",
            "headline": "AIxCC systems find 54 of 63 synthetic vulnerabilities, patch 43"
          }
        },
        "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": [
            "01edde86def16471a3fe4b3c89e5f67489b28fa09b20437cf77586aebe710a73"
          ],
          "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": "DARPA's results release describes the Final Competition. Teams' cyber reasoning systems tried to find and patch synthetic vulnerabilities across 54 million lines of real-world open-source code. They found 54 unique synthetic vulnerabilities in 63 challenges and patched 43. They also found 18 real, non-synthetic vulnerabilities (six in C codebases, 12 in Java), now being responsibly disclosed. There were 11 patches for real bugs. The average cost was about $152 per task. Team Atlanta (Georgia Tech, Samsung Research, KAIST, POSTECH) won $4 million, Trail of Bits $3 million and Theori $1.5 million. Four of seven systems were released open source. The Record reported the same figures from Las Vegas with program manager Andrew Carney's remarks. curl maintainer Daniel Stenberg, whose project was among the targets, examined the injected curl flaws. He judged them straightforward and not deeply hidden.",
            "replication": {
              "produced_by": [
                "Injected flaws in real open-source projects with scoring for proofs and patches",
                "Two years of funded development and frontier-lab model credits"
              ],
              "must_hold": [
                "Real-world codebases with harder, layered flaws than the injected ones",
                "Maintainer acceptance of machine-generated patches"
              ],
              "echoes": []
            }
          }
        },
        "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": 30,
      "reviewed": 0,
      "record_mapped": 30,
      "not_assessed": 61,
      "complete": false,
      "by_state": {
        "value_present": 30,
        "not_reported": 0,
        "unresolved": 0,
        "not_assessed": 61,
        "not_applicable": 0,
        "withheld": 0,
        "source_unavailable": 0
      }
    }
  }
}