{
  "schemaVersion": "ucr.full-study/1",
  "executedAt": "2026-08-10T17:31:13.862Z",
  "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": false,
        "crossSession": true,
        "crossProject": true,
        "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": "claude-code->codex",
    "families": null,
    "arms": "empty,runtime",
    "requestedArms": "empty,runtime",
    "maxTrials": 2,
    "selectedTrials": 2,
    "selectedTrialIdsHash": "97b8d742145106766dcbddae8271634e5945a8553263d5bb124f6b2110eb7318"
  },
  "qualification": {
    "schemaVersion": "ucr.study-qualification/1",
    "status": "failed",
    "passed": false,
    "checks": {
      "selectionComplete": true,
      "trialIntegrity": true,
      "taskCorrect": false,
      "runtimeDelivered": true,
      "controlsWithheld": true,
      "hardNegativesWithheld": true,
      "pairedCoverage": true,
      "correctnessNonInferiority": true,
      "tokenNonInferiority": true
    },
    "failed": [
      "taskCorrect"
    ],
    "selectedTrials": 2,
    "executedTrials": 2,
    "completePairs": 1,
    "maximumObservedTokenOverhead": -0.17122430244526665
  },
  "failures": [],
  "ledger": {
    "schemaVersion": "ucr.evidence-ledger/2",
    "evidenceClass": "executable-smoke",
    "run": {
      "schemaVersion": "ucr.evidence-run/2",
      "runId": "full-study-dc9aeea268e7f81f",
      "evidenceClass": "executable-smoke",
      "benchmarkHash": "597b75c9fb2a20a171bdde67c7a40cc5aef9aa27ee730550a747c750a39243d2",
      "sourceTreeHash": "e5f0f6751893c915c957266789ad14969833a975adc0c8d0bf0b1b1f99258fca",
      "runner": {
        "name": "ucr-full-study",
        "node": "v25.6.0",
        "planHash": "ea8fa07120d0046c15525d3311a47b0326a7309ce6c7403d3726a65c0791096f",
        "registrationHash": "e171d5da8431aa64f847b8bd5452b7f40facdb4330d0c21d6b6e38d89b486549",
        "poweredDesign": false,
        "minimumSubgroupPairs": 30
      },
      "startedAt": "2026-08-10T17:31:13.857Z",
      "runHash": "1773b5c1582dd85b393ab907574fb8c7f50bcdd628f526f21fba5a2c021fff3a"
    },
    "rows": [
      {
        "study": "full-effectiveness",
        "planHash": "ea8fa07120d0046c15525d3311a47b0326a7309ce6c7403d3726a65c0791096f",
        "trialId": "claude-code->codex:federation-001:0:empty",
        "pairId": "claude-code->codex:federation-001:0",
        "studySequence": 52,
        "taskId": "federation-001",
        "family": "cross-project-generalization",
        "arm": "empty",
        "direction": "claude-code->codex",
        "producerClient": "claude-code",
        "consumerClient": "codex",
        "producerFamily": "anthropic",
        "consumerFamily": "openai",
        "producerModel": "claude-sonnet-5",
        "consumerModel": "gpt-5.6-sol",
        "model": "gpt-5.6-sol",
        "modelVersion": "gpt-5.6-sol",
        "permissionsHash": "99cfc916f214c8e56d0093fa298b4e7f8739bd206e7452bbdfe25a9396338a38",
        "contextBudget": 160,
        "retryBudget": 1,
        "toolBudget": 40,
        "sessionMode": "cross-session",
        "projectMode": "cross-project",
        "agentMode": "single-successor",
        "expectedProviderInvocations": 2,
        "executionTopologyHash": "99f2ebb96e250c908ad7449f409a0ff35e1c6d3c5c1f853b26108fea1426c297",
        "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": 27452,
        "totalTokens": 35947,
        "latencyMs": 171295,
        "phaseAccounting": {
          "captureModelCalls": 0,
          "contextTokens": 0,
          "staticSchemaTokens": 0
        },
        "costLedger": {
          "costUsd": null,
          "source": "provider-cli-native"
        },
        "providerFailures": [],
        "causalClaim": false,
        "causalChain": null,
        "causalChainValid": false,
        "outcomeHash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a",
        "workspaceStateHash": "8ec80f4bdc5b4b4b483ecc28b4536080c51c86547d810d603ef53c9b0ddcbc99",
        "changedProtected": [],
        "trialIntegrityValid": true,
        "graderVerified": true,
        "graderReceiptHash": "d7223a4e45d671f9b428b3e9333b70702ff4244e7ddaa00fce5b6388d9d6e170",
        "runnerExitCode": 0,
        "runnerOutputHash": "c0557be8d70173cd1fcd550ed3ea7367487f02ce30146526df61807ad8ceabd9",
        "runnerErrorHash": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
        "schemaVersion": "ucr.evidence-row/2",
        "runId": "full-study-dc9aeea268e7f81f",
        "sequence": 0,
        "previousHash": "1773b5c1582dd85b393ab907574fb8c7f50bcdd628f526f21fba5a2c021fff3a",
        "rowHash": "f64e6d858b37ac50e8469b6f62f36e52cbf1dd48acb37237836645062f4863e1"
      },
      {
        "study": "full-effectiveness",
        "planHash": "ea8fa07120d0046c15525d3311a47b0326a7309ce6c7403d3726a65c0791096f",
        "trialId": "claude-code->codex:federation-001:0:runtime",
        "pairId": "claude-code->codex:federation-001:0",
        "studySequence": 551,
        "taskId": "federation-001",
        "family": "cross-project-generalization",
        "arm": "runtime",
        "direction": "claude-code->codex",
        "producerClient": "claude-code",
        "consumerClient": "codex",
        "producerFamily": "anthropic",
        "consumerFamily": "openai",
        "producerModel": "claude-sonnet-5",
        "consumerModel": "gpt-5.6-sol",
        "model": "gpt-5.6-sol",
        "modelVersion": "gpt-5.6-sol",
        "permissionsHash": "99cfc916f214c8e56d0093fa298b4e7f8739bd206e7452bbdfe25a9396338a38",
        "contextBudget": 160,
        "retryBudget": 1,
        "toolBudget": 40,
        "sessionMode": "cross-session",
        "projectMode": "cross-project",
        "agentMode": "single-successor",
        "expectedProviderInvocations": 2,
        "executionTopologyHash": "52c8a245c63f3a789640257921352cbcb66301faf0e652c34b2d35beedab82c0",
        "poweredStratum": false,
        "correct": false,
        "severeHarm": false,
        "mistakeExecuted": false,
        "knownMistake": false,
        "quarantinedBeforeNext": false,
        "applicable": true,
        "eligible": true,
        "selected": true,
        "delivered": true,
        "deliveryPhase": "pre-action",
        "stale": false,
        "contradictory": false,
        "contextOverheadRatio": 0.018714244157859012,
        "reconstructionTokens": 20626,
        "totalTokens": 29792,
        "latencyMs": 132444,
        "phaseAccounting": {
          "captureModelCalls": 0,
          "contextTokens": 386,
          "staticSchemaTokens": 0
        },
        "costLedger": {
          "costUsd": null,
          "source": "provider-cli-native"
        },
        "providerFailures": [],
        "causalClaim": false,
        "causalChain": null,
        "causalChainValid": false,
        "outcomeHash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a",
        "workspaceStateHash": "8ec80f4bdc5b4b4b483ecc28b4536080c51c86547d810d603ef53c9b0ddcbc99",
        "changedProtected": [],
        "trialIntegrityValid": true,
        "graderVerified": true,
        "graderReceiptHash": "33a8405937ccec0fdd2b114c4d7ea61fae984aac2b7b977fd2318145b6122ba4",
        "runnerExitCode": 0,
        "runnerOutputHash": "5821be9d3addb529d15bede54e646e4bc4fc854877d91293ba9818354de99fac",
        "runnerErrorHash": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
        "schemaVersion": "ucr.evidence-row/2",
        "runId": "full-study-dc9aeea268e7f81f",
        "sequence": 1,
        "previousHash": "f64e6d858b37ac50e8469b6f62f36e52cbf1dd48acb37237836645062f4863e1",
        "rowHash": "b9a2ba277906505dc7b2f57559955ea7f506be73166deff7656058e2bfd6379c"
      }
    ],
    "rowCount": 2,
    "chainHead": "b9a2ba277906505dc7b2f57559955ea7f506be73166deff7656058e2bfd6379c",
    "transcriptsPublished": false,
    "endedAt": "2026-08-10T17:31:13.858Z",
    "ledgerHash": "2a876004e74083afd9b572815de2f25d7275d8ece663a2ac334910de82e8a1a5",
    "signature": "fjIH3rYmjNupLbkXPTkZc7wYqRNE6DfS5F4RMTAE+lNMKL6UphCLHQD3VkcQyYWmHOdauzo9dIWtQcxk/MpRCQ=="
  },
  "ledgerKeyId": "ucr-ed25519-77b546af455c7ecd3c9c",
  "ledgerVerification": {
    "valid": true,
    "diagnostics": [],
    "validSignature": true,
    "ledgerHash": "2a876004e74083afd9b572815de2f25d7275d8ece663a2ac334910de82e8a1a5",
    "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": [
      "2a876004e74083afd9b572815de2f25d7275d8ece663a2ac334910de82e8a1a5"
    ],
    "rejectedLedgers": 0,
    "derivedHash": "f463c6be8c775adb8c37344134a03a9e17a962cebf1db411581c946ad9f3d7aa"
  },
  "costDiagnostics": {
    "passed": true,
    "thresholds": {
      "maximumTokenOverhead": 0.05,
      "maximumLatencyOverhead": 0.05
    },
    "groups": [
      {
        "dimension": "direction",
        "value": "claude-code->codex",
        "pairs": 1,
        "tokenOverhead": -0.17122430244526665,
        "latencyOverheadP95": -0.22680755421932922,
        "regressions": [],
        "passed": true
      },
      {
        "dimension": "family",
        "value": "cross-project-generalization",
        "pairs": 1,
        "tokenOverhead": -0.17122430244526665,
        "latencyOverheadP95": -0.22680755421932922,
        "regressions": [],
        "passed": true
      },
      {
        "dimension": "client",
        "value": "codex",
        "pairs": 1,
        "tokenOverhead": -0.17122430244526665,
        "latencyOverheadP95": -0.22680755421932922,
        "regressions": [],
        "passed": true
      }
    ]
  },
  "passed": false,
  "limitations": [
    "qualification or partial execution cannot supply effectiveness metrics"
  ],
  "reportHash": "8ebbbdd6e5ced34c2e703c3027f2c982646b1f3cb3ea25fa59c2df72d43db17a"
}