{
  "schemaVersion": "ucr.full-study/1",
  "executedAt": "2026-08-10T16:19:45.880Z",
  "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"
      },
      {
        "id": "claude-code",
        "model": "claude-sonnet-5",
        "modelFamily": "anthropic",
        "version": "2.1.225 (Claude Code)",
        "modelVersion": "claude-sonnet-5",
        "lifecycleFamily": "process-hook"
      },
      {
        "id": "gemini",
        "model": "gemini-2.5-pro",
        "modelFamily": "google",
        "version": "gemini-cli 0.28.1",
        "modelVersion": "gemini-2.5-pro",
        "lifecycleFamily": "process-hook"
      }
    ],
    "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": "8d0debfb4abd51a0da45754b1d232c17395fd5348a7c47971d2f69018dadbd93",
    "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": false,
        "isolatedWorkspaces": true,
        "materialVariants": false,
        "executionTopology": true
      },
      "coverage": {
        "families": 0.09090909090909091,
        "arms": 0.14285714285714285,
        "familyCount": 1,
        "requiredFamilies": 11,
        "armCount": 1,
        "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": 1,
  "selection": {
    "directions": "codex->gemini",
    "families": null,
    "arms": "empty",
    "requestedArms": "empty",
    "maxTrials": 1,
    "selectedTrials": 1,
    "selectedTrialIdsHash": "5dfb28fc49162ba20355c69e75cec0b1a1341507c09a4169b41e82ea3b79f5e8"
  },
  "qualification": {
    "schemaVersion": "ucr.study-qualification/1",
    "status": "failed",
    "passed": false,
    "checks": {
      "selectionComplete": false,
      "trialIntegrity": false,
      "taskCorrect": true,
      "runtimeDelivered": true,
      "controlsWithheld": true,
      "hardNegativesWithheld": true,
      "pairedCoverage": true,
      "correctnessNonInferiority": true,
      "tokenNonInferiority": true
    },
    "failed": [
      "selectionComplete",
      "trialIntegrity"
    ],
    "selectedTrials": 1,
    "executedTrials": 1,
    "completePairs": 0,
    "maximumObservedTokenOverhead": null
  },
  "failures": [
    {
      "trialId": "codex->gemini:adversarial-001:0:empty",
      "arm": "empty",
      "runnerExitCode": 1,
      "valid": false,
      "validation": [],
      "driverValidation": [
        "host action audit is incomplete",
        "provider-native total token accounting is missing",
        "executed CLI versions differ from the frozen plan",
        "executed model version differs from the frozen plan",
        "per-invocation phase telemetry is incomplete"
      ],
      "causalEvents": 0,
      "providerFailures": [
        {
          "classification": "provider-client-migration-required",
          "role": "consumer-1"
        }
      ],
      "rowHash": "a26267f7ddc27a10ab3336fb45ecd544cae6d34c5d940612a708a7cfe829058f"
    }
  ],
  "ledger": {
    "schemaVersion": "ucr.evidence-ledger/2",
    "evidenceClass": "executable-smoke",
    "run": {
      "schemaVersion": "ucr.evidence-run/2",
      "runId": "full-study-a7807cd0826ff8a0",
      "evidenceClass": "executable-smoke",
      "benchmarkHash": "597b75c9fb2a20a171bdde67c7a40cc5aef9aa27ee730550a747c750a39243d2",
      "sourceTreeHash": "b9eec6eae3d1a7f92fae68a8bec9ec3cccad7e4617895626c5e23101a250b0d4",
      "runner": {
        "name": "ucr-full-study",
        "node": "v25.6.0",
        "planHash": "8d0debfb4abd51a0da45754b1d232c17395fd5348a7c47971d2f69018dadbd93",
        "registrationHash": "e171d5da8431aa64f847b8bd5452b7f40facdb4330d0c21d6b6e38d89b486549",
        "poweredDesign": false,
        "minimumSubgroupPairs": 30
      },
      "startedAt": "2026-08-10T16:19:45.875Z",
      "runHash": "3943e306599496834701f304902dd14ff5bc1eaaf5151edf2927dc8f9bbcf7d1"
    },
    "rows": [
      {
        "study": "full-effectiveness",
        "planHash": "8d0debfb4abd51a0da45754b1d232c17395fd5348a7c47971d2f69018dadbd93",
        "trialId": "codex->gemini:adversarial-001:0:empty",
        "pairId": "codex->gemini:adversarial-001:0",
        "studySequence": 23,
        "taskId": "adversarial-001",
        "family": "adversarial-memory",
        "arm": "empty",
        "direction": "codex->gemini",
        "producerClient": "codex",
        "consumerClient": "gemini",
        "producerFamily": "openai",
        "consumerFamily": "google",
        "producerModel": "gpt-5.6-sol",
        "consumerModel": "gemini-2.5-pro",
        "model": "gemini-2.5-pro",
        "modelVersion": null,
        "permissionsHash": "99cfc916f214c8e56d0093fa298b4e7f8739bd206e7452bbdfe25a9396338a38",
        "contextBudget": 160,
        "retryBudget": 1,
        "toolBudget": 40,
        "sessionMode": "same-session",
        "projectMode": "same-project",
        "agentMode": "single-successor",
        "expectedProviderInvocations": 2,
        "executionTopologyHash": "0b944e194f2c7261be0dfb240e752e3cfb41c95830299cb7b0f015ecffe7e080",
        "poweredStratum": false,
        "correct": false,
        "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": null,
        "totalTokens": null,
        "latencyMs": 45345,
        "phaseAccounting": {
          "captureModelCalls": 0,
          "contextTokens": 0,
          "staticSchemaTokens": 0
        },
        "costLedger": {
          "costUsd": null,
          "source": "provider-cli-native"
        },
        "providerFailures": [
          {
            "classification": "provider-client-migration-required",
            "role": "consumer-1"
          }
        ],
        "causalClaim": false,
        "causalChain": null,
        "causalChainValid": false,
        "outcomeHash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a",
        "workspaceStateHash": "6f57f10a472583c0e8ed3ae52e682e812c8a47f6f6e9b10ed309307938c0948a",
        "changedProtected": [],
        "trialIntegrityValid": false,
        "graderVerified": true,
        "graderReceiptHash": "a0c638aca09379cebcd2984291ba99eb6a83f651597638019b9660bb4a14a221",
        "runnerExitCode": 1,
        "runnerOutputHash": "a50a07de3d366c1589d6556e4e149d7d473ea0eba795e47383df36464403c64b",
        "runnerErrorHash": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
        "schemaVersion": "ucr.evidence-row/2",
        "runId": "full-study-a7807cd0826ff8a0",
        "sequence": 0,
        "previousHash": "3943e306599496834701f304902dd14ff5bc1eaaf5151edf2927dc8f9bbcf7d1",
        "rowHash": "cbbde1a76ccbdacbd68aeaffd7c9aa8ef9075993df0515e4ff685d5432425750"
      }
    ],
    "rowCount": 1,
    "chainHead": "cbbde1a76ccbdacbd68aeaffd7c9aa8ef9075993df0515e4ff685d5432425750",
    "transcriptsPublished": false,
    "endedAt": "2026-08-10T16:19:45.876Z",
    "ledgerHash": "1b259bd70702aa27b41861c2f721debeaeedd874f1435351f3b1af4ad4b59188",
    "signature": "xdoyHhvl+NuIMRJQGKONsWGfTXsGu1CU+4jed/vmJuWOW+g9fXJpC6a7RF4tSYHiI+aQD1rJFzpf3hsmHLcSBQ=="
  },
  "ledgerKeyId": "ucr-ed25519-77b546af455c7ecd3c9c",
  "ledgerVerification": {
    "valid": true,
    "diagnostics": [],
    "validSignature": true,
    "ledgerHash": "1b259bd70702aa27b41861c2f721debeaeedd874f1435351f3b1af4ad4b59188",
    "rowCount": 1
  },
  "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": [
      "1b259bd70702aa27b41861c2f721debeaeedd874f1435351f3b1af4ad4b59188"
    ],
    "rejectedLedgers": 0,
    "derivedHash": "a614d22d2d7ef9407f022ace66ec7fc5b5620afd5a6eaa07ccfb7fd2e91aa7f3"
  },
  "costDiagnostics": {
    "passed": false,
    "thresholds": {
      "maximumTokenOverhead": 0.05,
      "maximumLatencyOverhead": 0.05
    },
    "groups": []
  },
  "passed": false,
  "limitations": [
    "qualification or partial execution cannot supply effectiveness metrics"
  ],
  "reportHash": "be2097b18a46e28c9e916e69ae9a8914d6680e17e5f7aaa67b0c262686b25242"
}