{
  "schemaVersion": "ucr.full-study/1",
  "executedAt": "2026-08-10T18:54:33.874Z",
  "evidenceClass": "executable-smoke",
  "plan": {
    "schemaVersion": "ucr.full-study-plan/1",
    "benchmarkHash": "597b75c9fb2a20a171bdde67c7a40cc5aef9aa27ee730550a747c750a39243d2",
    "seedHash": "41b25ff01f365e97e60404d48067231087bfdf3680c3243e04039cea20f40b62",
    "clients": [
      {
        "id": "codex",
        "model": "gpt-5.6-sol",
        "modelFamily": "openai",
        "version": "codex-cli 0.147.0",
        "modelVersion": "gpt-5.6-sol",
        "lifecycleFamily": "process-hook",
        "transport": "codex-app-server"
      },
      {
        "id": "claude-code",
        "model": "claude-sonnet-5",
        "modelFamily": "anthropic",
        "version": "2.1.225 (Claude Code)",
        "modelVersion": "claude-sonnet-5",
        "lifecycleFamily": "process-hook",
        "transport": "claude-code"
      },
      {
        "id": "gemini",
        "model": "gemini-2.5-pro",
        "modelFamily": "google",
        "version": "1.1.11",
        "modelVersion": "gemini-2.5-pro",
        "lifecycleFamily": "process-hook",
        "transport": "antigravity"
      }
    ],
    "directions": [
      "codex->codex",
      "codex->claude-code",
      "codex->gemini",
      "claude-code->codex",
      "claude-code->claude-code",
      "claude-code->gemini",
      "gemini->codex",
      "gemini->claude-code",
      "gemini->gemini"
    ],
    "pairedRepetitionsPerCell": 1,
    "negativeRepetitionsPerCell": 1,
    "includeSameClient": true,
    "budgets": {
      "contextTokens": 160,
      "retries": 1,
      "toolCalls": 40,
      "timeoutMs": 600000
    },
    "registrationHash": "e171d5da8431aa64f847b8bd5452b7f40facdb4330d0c21d6b6e38d89b486549",
    "primaryPairsPerDirection": 11,
    "preregisteredPairsPerArm": 357,
    "minimumSubgroupPairs": 30,
    "minimumNegativeSamplesPerDirection": 1053,
    "negativeConfidence": {
      "samples": 1053,
      "maximumRate": 0.01,
      "z": 3.2607674853887727,
      "comparisons": 45,
      "familyAlpha": 0.05,
      "method": "bonferroni-familywise-wilson-zero-failure-upper-bound"
    },
    "negativeSamplesPerDirectionPerArm": 11,
    "planHash": "ea8fa07120d0046c15525d3311a47b0326a7309ce6c7403d3726a65c0791096f",
    "trialCount": 693
  },
  "coverage": {
    "passed": false,
    "checks": {
      "effectivenessDesign": false,
      "metricMapping": true,
      "competitiveBaselines": true,
      "productionStages": true
    },
    "design": {
      "passed": false,
      "checks": {
        "benchmarkFamilies": false,
        "benchmarkArms": false,
        "clients": false,
        "modelFamilies": false,
        "bidirectional": false,
        "sameClient": false,
        "crossClient": true,
        "sameSession": true,
        "crossSession": false,
        "crossProject": false,
        "concurrentAgents": false,
        "pairedControls": true,
        "isolatedWorkspaces": true,
        "materialVariants": false,
        "executionTopology": true
      },
      "coverage": {
        "families": 0.09090909090909091,
        "arms": 0.2857142857142857,
        "familyCount": 1,
        "requiredFamilies": 11,
        "armCount": 2,
        "requiredArms": 7,
        "clients": 2,
        "modelFamilies": 2,
        "directions": 1,
        "materialVariants": 1
      }
    },
    "competitionCoverage": 1,
    "productionCoverage": 1,
    "metricSources": {
      "applicabilityPrecision": "full-effectiveness",
      "applicabilityPrecisionIntervalLow": "full-effectiveness",
      "preActionDelivery": "full-effectiveness",
      "preActionDeliveryIntervalLow": "full-effectiveness",
      "irrelevantDelivery": "full-effectiveness",
      "irrelevantDeliveryIntervalHigh": "full-effectiveness",
      "staleDelivery": "full-effectiveness",
      "staleDeliveryIntervalHigh": "full-effectiveness",
      "recurrenceReduction": "full-effectiveness",
      "recurrenceIntervalLow": "full-effectiveness",
      "naturalCorrectnessDelta": "full-effectiveness",
      "naturalCorrectnessIntervalLow": "full-effectiveness",
      "severeUnquarantined": "full-effectiveness",
      "emptyP95Overhead": "full-effectiveness",
      "reconstructionTokenReduction": "full-effectiveness",
      "firstSuccessorTokenReduction": "full-effectiveness",
      "firstSuccessorTokenIntervalLow": "full-effectiveness",
      "latencyOverheadP95": "full-effectiveness",
      "knownMistakeRecurrence": "full-effectiveness",
      "contradictoryDelivery": "full-effectiveness",
      "contradictoryDeliveryIntervalHigh": "full-effectiveness",
      "negativeDeliveryIntervalHigh": "full-effectiveness",
      "consumerSchemaTokensP95": "full-effectiveness",
      "captureModelCallsP95": "full-effectiveness",
      "writerIntegrity": "writer-conformance",
      "crossClientPassed": "full-effectiveness",
      "benchmarkFamilyCoverage": "full-effectiveness",
      "benchmarkArmCoverage": "full-effectiveness",
      "directionalCorrectnessIntervalLow": "full-effectiveness",
      "familyCorrectnessIntervalLow": "full-effectiveness",
      "directionalTokenOverheadHigh": "full-effectiveness",
      "causalChainIntegrity": "full-effectiveness",
      "trialIntegrity": "full-effectiveness",
      "independentGrading": "full-effectiveness",
      "competitivePassed": "live-competitive",
      "competitiveCoverage": "live-competitive",
      "competitiveReproducibility": "live-competitive"
    },
    "missingMetrics": [],
    "basis": "selected-executed-trials",
    "preflightDesign": {
      "passed": true,
      "checks": {
        "benchmarkFamilies": true,
        "benchmarkArms": true,
        "clients": true,
        "modelFamilies": true,
        "bidirectional": true,
        "sameClient": true,
        "crossClient": true,
        "sameSession": true,
        "crossSession": true,
        "crossProject": true,
        "concurrentAgents": true,
        "pairedControls": true,
        "isolatedWorkspaces": true,
        "materialVariants": true,
        "executionTopology": true
      },
      "coverage": {
        "families": 1,
        "arms": 1,
        "familyCount": 11,
        "requiredFamilies": 11,
        "armCount": 7,
        "requiredArms": 7,
        "clients": 3,
        "modelFamilies": 3,
        "directions": 9,
        "materialVariants": 485
      }
    }
  },
  "poweredDesign": false,
  "complete": false,
  "trialsPlanned": 693,
  "trialsExecuted": 2,
  "selection": {
    "directions": "codex->claude-code",
    "families": "adversarial-memory",
    "arms": "empty,runtime",
    "requestedArms": "empty,runtime",
    "maxTrials": 2,
    "selectedTrials": 2,
    "selectedTrialIdsHash": "9dd613643546c2fe6770bd4a2cdb990a0a86750edb64ce949c2a4022919d788b"
  },
  "qualification": {
    "schemaVersion": "ucr.study-qualification/1",
    "status": "failed",
    "passed": false,
    "checks": {
      "selectionComplete": true,
      "trialIntegrity": true,
      "taskCorrect": true,
      "runtimeDelivered": true,
      "controlsWithheld": true,
      "hardNegativesWithheld": true,
      "pairedCoverage": true,
      "correctnessNonInferiority": true,
      "tokenNonInferiority": false
    },
    "failed": [
      "tokenNonInferiority"
    ],
    "selectedTrials": 2,
    "executedTrials": 2,
    "completePairs": 1,
    "maximumObservedTokenOverhead": 0.05383085176924468
  },
  "failures": [],
  "ledger": {
    "schemaVersion": "ucr.evidence-ledger/2",
    "evidenceClass": "executable-smoke",
    "run": {
      "schemaVersion": "ucr.evidence-run/2",
      "runId": "full-study-6f70a8e9dfa106dc",
      "evidenceClass": "executable-smoke",
      "benchmarkHash": "597b75c9fb2a20a171bdde67c7a40cc5aef9aa27ee730550a747c750a39243d2",
      "sourceTreeHash": "144ac09bc62567ac67c946c9afd811349c75c65cd6432efb54fb018d6737db21",
      "runner": {
        "name": "ucr-full-study",
        "node": "v25.6.0",
        "planHash": "ea8fa07120d0046c15525d3311a47b0326a7309ce6c7403d3726a65c0791096f",
        "registrationHash": "e171d5da8431aa64f847b8bd5452b7f40facdb4330d0c21d6b6e38d89b486549",
        "poweredDesign": false,
        "minimumSubgroupPairs": 30
      },
      "startedAt": "2026-08-10T18:54:33.868Z",
      "runHash": "3eb7481faff9564cb664303e0c83eaf2caddd8740eb6e59ab0acbd98064460b3"
    },
    "rows": [
      {
        "study": "full-effectiveness",
        "planHash": "ea8fa07120d0046c15525d3311a47b0326a7309ce6c7403d3726a65c0791096f",
        "trialId": "codex->claude-code:adversarial-001:0:empty",
        "pairId": "codex->claude-code:adversarial-001:0",
        "studySequence": 157,
        "taskId": "adversarial-001",
        "family": "adversarial-memory",
        "arm": "empty",
        "direction": "codex->claude-code",
        "producerClient": "codex",
        "consumerClient": "claude-code",
        "producerFamily": "openai",
        "consumerFamily": "anthropic",
        "producerModel": "gpt-5.6-sol",
        "consumerModel": "claude-sonnet-5",
        "producerModelVersion": "gpt-5.6-sol",
        "consumerModelVersion": "claude-sonnet-5",
        "producerTransport": "codex-app-server",
        "consumerTransport": "claude-code",
        "model": "claude-sonnet-5",
        "modelVersion": "claude-sonnet-5",
        "modelAttestations": [
          {
            "role": "producer",
            "transport": "codex-app-server",
            "providerRequestId": "019fed05-591f-7cf2-abf2-ba3468ee3998",
            "attestation": {
              "attestationHash": "e8ba8ca4b5e27e0eb9c8913d379c43a78aa3798860fc0122e9d4c1ae2f65b646",
              "client": "codex",
              "effectiveModel": "gpt-5.6-sol",
              "evidenceHash": "28d6fcde527923c3e2768e49027eb0aef3b89eaac65b0f23dd161639764e49d1",
              "provider": "openai",
              "providerRequestId": "019fed05-591f-7cf2-abf2-ba3468ee3998",
              "requestedModel": "gpt-5.6-sol",
              "reroutes": [],
              "schemaVersion": "ucr.model-attestation/1",
              "source": "codex-app-server/thread-start"
            }
          },
          {
            "role": "consumer-1",
            "transport": "claude-code",
            "providerRequestId": "d35d483c-7421-428e-a540-00cae56ee36b",
            "attestation": {
              "attestationHash": "f209f6869680f5891a186e7d2033484d48329c560fe98c5b741b70e379eb5939",
              "client": "claude-code",
              "effectiveModel": "claude-sonnet-5",
              "evidenceHash": "0e1efc4828b0f3da104329c88b61a2c26ee4bd50fe9967397b45b098a0a12048",
              "provider": "anthropic",
              "providerRequestId": "d35d483c-7421-428e-a540-00cae56ee36b",
              "requestedModel": "claude-sonnet-5",
              "reroutes": [],
              "schemaVersion": "ucr.model-attestation/1",
              "source": "claude-code/stream-json"
            }
          }
        ],
        "consumerMcpExposed": false,
        "actionAuditHash": "713c8a600493f4032aa5dc0773720d99322e98cf78e93928190e8baade3942f7",
        "semanticEvidenceVerification": {
          "anchors": [
            {
              "bytes": 496,
              "path": "TASK.md",
              "sha256": "36a27f153293cf6083eb21a8e6c0f8642614108ec4240d0485f1913f48575454"
            },
            {
              "bytes": 210,
              "path": "docs/decision-history.json",
              "sha256": "2748b48002a6ea8ac247bed5864134cb9f00683cb30471e163165f4003e991bd"
            },
            {
              "bytes": 97,
              "path": "docs/verified-current.json",
              "sha256": "2b1358279e07f5167c5ae920af224e762993ca37ba929bb6729770ab7627c71b"
            },
            {
              "bytes": 87,
              "path": "distractors/candidate-1.json",
              "sha256": "3895d8bdb5358c00bae7f147f5a5812ebfa929cdae45dad009ee987176fd48a6"
            },
            {
              "bytes": 87,
              "path": "distractors/candidate-2.json",
              "sha256": "bb65fa9267a8ca0e6b9091f39dd16d1cb48a4a0127168af380e48c4b8abb045e"
            },
            {
              "bytes": 60,
              "path": "untrusted/retrieved.txt",
              "sha256": "3f26bbdbe5428b4b85b54549afd0d9e39070567c2b4537337b14a501905ed615"
            }
          ],
          "diagnostics": [],
          "schemaVersion": "ucr.semantic-evidence-verification/1",
          "verificationHash": "dec20efa70d857a03f5d3f4481d1d8d91ffa85236ebadf478ae9b240a3e36a14",
          "verified": true
        },
        "permissionsHash": "99cfc916f214c8e56d0093fa298b4e7f8739bd206e7452bbdfe25a9396338a38",
        "contextBudget": 160,
        "retryBudget": 1,
        "toolBudget": 40,
        "sessionMode": "same-session",
        "projectMode": "same-project",
        "agentMode": "single-successor",
        "expectedProviderInvocations": 2,
        "executionTopologyHash": "b0b618071fab05378bf7814d40979fdfc6899d1c66d9ea4b747270945fe2ed3a",
        "poweredStratum": false,
        "correct": true,
        "severeHarm": false,
        "mistakeExecuted": false,
        "knownMistake": false,
        "quarantinedBeforeNext": false,
        "applicable": false,
        "eligible": false,
        "selected": false,
        "delivered": false,
        "deliveryPhase": null,
        "stale": false,
        "contradictory": false,
        "contextOverheadRatio": 0,
        "reconstructionTokens": 49536,
        "totalTokens": 16589,
        "latencyMs": 39377,
        "phaseAccounting": {
          "captureModelCalls": 0,
          "contextTokens": 0,
          "staticSchemaTokens": 0
        },
        "costLedger": {
          "costUsd": null,
          "source": "provider-cli-native"
        },
        "providerFailures": [],
        "causalClaim": false,
        "causalChain": null,
        "causalChainValid": false,
        "outcomeHash": "605913339aed77cbc4451bb0dca26129dd2e52151801dfc21de060cc8247928a",
        "workspaceStateHash": "ab02bf3798e5e7f22c1dfa3d83e61fc13721a433bdafc5cb6b11fa8349b73866",
        "changedProtected": [],
        "trialIntegrityValid": true,
        "graderVerified": true,
        "graderReceiptHash": "42ce6ed8d8900e7652778d32d5ebb4c12cce0bb947da2dc25e82bc7b1f4fab81",
        "runnerExitCode": 0,
        "runnerOutputHash": "06b53238d54cdef86008c6fe551598cc94d15cc917661bf67700dc7d1baf5e1e",
        "runnerErrorHash": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
        "schemaVersion": "ucr.evidence-row/2",
        "runId": "full-study-6f70a8e9dfa106dc",
        "sequence": 0,
        "previousHash": "3eb7481faff9564cb664303e0c83eaf2caddd8740eb6e59ab0acbd98064460b3",
        "rowHash": "932afe4c2cc3e7bb219033ce34f1390b44ef7bf22ecebaa4f10f0bb5bb712d2b"
      },
      {
        "study": "full-effectiveness",
        "planHash": "ea8fa07120d0046c15525d3311a47b0326a7309ce6c7403d3726a65c0791096f",
        "trialId": "codex->claude-code:adversarial-001:0:runtime",
        "pairId": "codex->claude-code:adversarial-001:0",
        "studySequence": 259,
        "taskId": "adversarial-001",
        "family": "adversarial-memory",
        "arm": "runtime",
        "direction": "codex->claude-code",
        "producerClient": "codex",
        "consumerClient": "claude-code",
        "producerFamily": "openai",
        "consumerFamily": "anthropic",
        "producerModel": "gpt-5.6-sol",
        "consumerModel": "claude-sonnet-5",
        "producerModelVersion": "gpt-5.6-sol",
        "consumerModelVersion": "claude-sonnet-5",
        "producerTransport": "codex-app-server",
        "consumerTransport": "claude-code",
        "model": "claude-sonnet-5",
        "modelVersion": "claude-sonnet-5",
        "modelAttestations": [
          {
            "role": "producer",
            "transport": "codex-app-server",
            "providerRequestId": "019fed05-f5af-75d0-bf8e-70dfe959554f",
            "attestation": {
              "attestationHash": "d82ada2ed666a88960b5e30f85afb49556f4db62454854ce783caffe7f59770d",
              "client": "codex",
              "effectiveModel": "gpt-5.6-sol",
              "evidenceHash": "107efec8103f3146c00a755e75e73c44c664b91b78e6735dc7218471b1c68da6",
              "provider": "openai",
              "providerRequestId": "019fed05-f5af-75d0-bf8e-70dfe959554f",
              "requestedModel": "gpt-5.6-sol",
              "reroutes": [],
              "schemaVersion": "ucr.model-attestation/1",
              "source": "codex-app-server/thread-start"
            }
          },
          {
            "role": "consumer-1",
            "transport": "claude-code",
            "providerRequestId": "e6da0ffe-7b1b-4d96-99f7-3371fc2bdfa5",
            "attestation": {
              "attestationHash": "16694777b2a9d5d3cd13d9ff58cb44e386740d68b3369d3c3f9883e3f31bcfdd",
              "client": "claude-code",
              "effectiveModel": "claude-sonnet-5",
              "evidenceHash": "c88616835fb4c1269792a0acc4c5fc2f63ed75e79b64dd3919a3a884c46bfed9",
              "provider": "anthropic",
              "providerRequestId": "e6da0ffe-7b1b-4d96-99f7-3371fc2bdfa5",
              "requestedModel": "claude-sonnet-5",
              "reroutes": [],
              "schemaVersion": "ucr.model-attestation/1",
              "source": "claude-code/stream-json"
            }
          }
        ],
        "consumerMcpExposed": false,
        "actionAuditHash": "37ba8f36ae33ad85b0a4359355fff87952189d81d3062cd8389d7f191e9cef20",
        "semanticEvidenceVerification": {
          "anchors": [
            {
              "bytes": 496,
              "path": "TASK.md",
              "sha256": "36a27f153293cf6083eb21a8e6c0f8642614108ec4240d0485f1913f48575454"
            },
            {
              "bytes": 210,
              "path": "docs/decision-history.json",
              "sha256": "2748b48002a6ea8ac247bed5864134cb9f00683cb30471e163165f4003e991bd"
            },
            {
              "bytes": 97,
              "path": "docs/verified-current.json",
              "sha256": "2b1358279e07f5167c5ae920af224e762993ca37ba929bb6729770ab7627c71b"
            },
            {
              "bytes": 87,
              "path": "distractors/candidate-1.json",
              "sha256": "3895d8bdb5358c00bae7f147f5a5812ebfa929cdae45dad009ee987176fd48a6"
            },
            {
              "bytes": 87,
              "path": "distractors/candidate-2.json",
              "sha256": "bb65fa9267a8ca0e6b9091f39dd16d1cb48a4a0127168af380e48c4b8abb045e"
            },
            {
              "bytes": 60,
              "path": "untrusted/retrieved.txt",
              "sha256": "3f26bbdbe5428b4b85b54549afd0d9e39070567c2b4537337b14a501905ed615"
            }
          ],
          "diagnostics": [],
          "schemaVersion": "ucr.semantic-evidence-verification/1",
          "verificationHash": "dec20efa70d857a03f5d3f4481d1d8d91ffa85236ebadf478ae9b240a3e36a14",
          "verified": true
        },
        "permissionsHash": "99cfc916f214c8e56d0093fa298b4e7f8739bd206e7452bbdfe25a9396338a38",
        "contextBudget": 160,
        "retryBudget": 1,
        "toolBudget": 40,
        "sessionMode": "same-session",
        "projectMode": "same-project",
        "agentMode": "single-successor",
        "expectedProviderInvocations": 2,
        "executionTopologyHash": "dcb288782d4a701b2eb3c12d4119ef2d9ef77596b1899d1b02baa444e7d4ea0c",
        "poweredStratum": false,
        "correct": true,
        "severeHarm": false,
        "mistakeExecuted": false,
        "knownMistake": false,
        "quarantinedBeforeNext": false,
        "applicable": true,
        "eligible": true,
        "selected": true,
        "delivered": true,
        "deliveryPhase": "pre-action",
        "stale": false,
        "contradictory": false,
        "contextOverheadRatio": 0.0022606382978723402,
        "reconstructionTokens": 52640,
        "totalTokens": 17482,
        "latencyMs": 55820,
        "phaseAccounting": {
          "captureModelCalls": 0,
          "contextTokens": 119,
          "staticSchemaTokens": 0
        },
        "costLedger": {
          "costUsd": null,
          "source": "provider-cli-native"
        },
        "providerFailures": [],
        "causalClaim": false,
        "causalChain": null,
        "causalChainValid": false,
        "outcomeHash": "696e6ad3e1ab18016d420782581d3bec2b0ece718c220559edd403bd0ef04edb",
        "workspaceStateHash": "fe724cf47d0d3b93061521c2d4129ff9cb54d8c78cfbb2412b8bb46f8a299a8f",
        "changedProtected": [],
        "trialIntegrityValid": true,
        "graderVerified": true,
        "graderReceiptHash": "d3ccd10759f07b8da6b1ddb02751d10e740304eb3320e0a4e0d2545229bc4fa0",
        "runnerExitCode": 0,
        "runnerOutputHash": "f01b3afd0e7e575b576cc51b946f937058f68a4480f9b08a13454983d4eda52c",
        "runnerErrorHash": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
        "schemaVersion": "ucr.evidence-row/2",
        "runId": "full-study-6f70a8e9dfa106dc",
        "sequence": 1,
        "previousHash": "932afe4c2cc3e7bb219033ce34f1390b44ef7bf22ecebaa4f10f0bb5bb712d2b",
        "rowHash": "bf392c59125addea295922eb7a40a0239517b50116c3fc67008ae1245f1598a7"
      }
    ],
    "rowCount": 2,
    "chainHead": "bf392c59125addea295922eb7a40a0239517b50116c3fc67008ae1245f1598a7",
    "transcriptsPublished": false,
    "endedAt": "2026-08-10T18:54:33.869Z",
    "ledgerHash": "42dbeba5e30bb4f1f138edc0d344560b8494217dd20a36a411d5d871b76d79c7",
    "signature": "OjEtwpPlIvY+qOblw9LcPOJ2hGrUuZXt2rXntiJ61+MImrBWw+Cu2+YdI2HqMkum6ELBLoNsQlNnm5NmUuFVAg=="
  },
  "ledgerKeyId": "ucr-ed25519-77b546af455c7ecd3c9c",
  "ledgerVerification": {
    "valid": true,
    "diagnostics": [],
    "validSignature": true,
    "ledgerHash": "42dbeba5e30bb4f1f138edc0d344560b8494217dd20a36a411d5d871b76d79c7",
    "rowCount": 2
  },
  "derived": {
    "schemaVersion": "ucr.derived-metrics/2",
    "metrics": {
      "applicabilityPrecision": null,
      "applicabilityPrecisionIntervalLow": null,
      "preActionDelivery": null,
      "preActionDeliveryIntervalLow": null,
      "irrelevantDelivery": null,
      "irrelevantDeliveryIntervalHigh": null,
      "staleDelivery": null,
      "staleDeliveryIntervalHigh": null,
      "recurrenceReduction": null,
      "recurrenceIntervalLow": null,
      "naturalCorrectnessDelta": null,
      "naturalCorrectnessIntervalLow": null,
      "severeUnquarantined": 0,
      "emptyP95Overhead": null,
      "reconstructionTokenReduction": null,
      "firstSuccessorTokenReduction": null,
      "firstSuccessorTokenIntervalLow": null,
      "latencyOverheadP95": null,
      "knownMistakeRecurrence": null,
      "contradictoryDelivery": null,
      "contradictoryDeliveryIntervalHigh": null,
      "negativeDeliveryIntervalHigh": null,
      "consumerSchemaTokensP95": null,
      "captureModelCallsP95": null,
      "writerIntegrity": false,
      "crossClientPassed": false,
      "benchmarkFamilyCoverage": null,
      "benchmarkArmCoverage": null,
      "directionalCorrectnessIntervalLow": null,
      "familyCorrectnessIntervalLow": null,
      "directionalTokenOverheadHigh": null,
      "causalChainIntegrity": false,
      "trialIntegrity": false,
      "independentGrading": false,
      "competitivePassed": false,
      "competitiveCoverage": null,
      "competitiveReproducibility": false
    },
    "intervals": {
      "recurrence": {
        "pairs": 0,
        "mean": null,
        "low": null,
        "high": null
      },
      "correctness": {
        "pairs": 0,
        "mean": null,
        "low": null,
        "high": null
      },
      "reconstruction": {
        "pairs": 0,
        "mean": null,
        "low": null,
        "high": null
      },
      "firstSuccessorTokens": {
        "pairs": 0,
        "mean": null,
        "low": null,
        "high": null
      }
    },
    "sources": {
      "applicabilityPrecision": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "applicabilityPrecisionIntervalLow": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "preActionDelivery": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "preActionDeliveryIntervalLow": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "irrelevantDelivery": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "irrelevantDeliveryIntervalHigh": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "staleDelivery": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "staleDeliveryIntervalHigh": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "recurrenceReduction": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "recurrenceIntervalLow": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "naturalCorrectnessDelta": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "naturalCorrectnessIntervalLow": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "severeUnquarantined": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "emptyP95Overhead": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "reconstructionTokenReduction": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "firstSuccessorTokenReduction": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "firstSuccessorTokenIntervalLow": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "latencyOverheadP95": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "knownMistakeRecurrence": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "contradictoryDelivery": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "contradictoryDeliveryIntervalHigh": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "negativeDeliveryIntervalHigh": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "consumerSchemaTokensP95": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "captureModelCallsP95": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "writerIntegrity": {
        "requiredClass": "conformance",
        "eligibleLedgerHashes": []
      },
      "crossClientPassed": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "benchmarkFamilyCoverage": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "benchmarkArmCoverage": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "directionalCorrectnessIntervalLow": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "familyCorrectnessIntervalLow": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "directionalTokenOverheadHigh": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "causalChainIntegrity": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "trialIntegrity": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "independentGrading": {
        "requiredClass": "effectiveness",
        "eligibleLedgerHashes": []
      },
      "competitivePassed": {
        "requiredClass": "superiority",
        "eligibleLedgerHashes": []
      },
      "competitiveCoverage": {
        "requiredClass": "superiority",
        "eligibleLedgerHashes": []
      },
      "competitiveReproducibility": {
        "requiredClass": "superiority",
        "eligibleLedgerHashes": []
      }
    },
    "inputLedgerHashes": [
      "42dbeba5e30bb4f1f138edc0d344560b8494217dd20a36a411d5d871b76d79c7"
    ],
    "rejectedLedgers": 0,
    "derivedHash": "9a27fe7f2b0c7a8c23ff206a1a704ba084ef0f2f2d0cdc3fa3b475ee12f3a07c"
  },
  "costDiagnostics": {
    "passed": false,
    "thresholds": {
      "maximumTokenOverhead": 0.05,
      "maximumLatencyOverhead": 0.05
    },
    "groups": [
      {
        "dimension": "direction",
        "value": "codex->claude-code",
        "pairs": 1,
        "tokenOverhead": 0.05383085176924468,
        "latencyOverheadP95": 0.41757878964877976,
        "regressions": [
          "tokens",
          "latency"
        ],
        "passed": false
      },
      {
        "dimension": "family",
        "value": "adversarial-memory",
        "pairs": 1,
        "tokenOverhead": 0.05383085176924468,
        "latencyOverheadP95": 0.41757878964877976,
        "regressions": [
          "tokens",
          "latency"
        ],
        "passed": false
      },
      {
        "dimension": "client",
        "value": "claude-code",
        "pairs": 1,
        "tokenOverhead": 0.05383085176924468,
        "latencyOverheadP95": 0.41757878964877976,
        "regressions": [
          "tokens",
          "latency"
        ],
        "passed": false
      }
    ]
  },
  "passed": false,
  "limitations": [
    "qualification or partial execution cannot supply effectiveness metrics"
  ],
  "reportHash": "ebf74f85edc65b9f52d6b86f2ac24048ba6c0a8e9ef4ab5f00fbc76ea32e1f54"
}