{
  "type": "controlled-study-ab-result",
  "schemaVersion": 1,
  "resultVersion": "v1",
  "round": "ab-adjudicated-cost-2026-08-31",
  "runId": "phase-9-ab-adjudicated-cost-03",
  "planHash": "f61bf70063fcceb9dfe823ac9d0707f0f004a075143cae6e9518523c64ba1b4f",
  "ledgerHash": "cc3eb8a816f961b4a4d8fdefd96365e6b89f3fd7d5aad287c3c5cc79a80ed0f5",
  "metricsReportHash": "d2849c3515da91385af91e9a80b70fa25b5f2ad6f248255229aba6ce73b3fd22",
  "sample": {
    "taskCount": 24,
    "modelCount": 2,
    "scenarioCount": 2,
    "observationsPerArm": 48,
    "pairedComparisons": 48
  },
  "arms": [
    {
      "scenarioId": "repository-only",
      "observationCount": 48,
      "executionStatus": { "completed": 36, "budget-exceeded": 11, "timed-out": 1 },
      "completedRate": 0.75,
      "taskOutcome": { "success": 3, "partial": 34, "blocked": 10, "missing": 1 },
      "adjudicationOutcome": { "success": 0, "partial": 33, "blocked": 13, "incomplete": 2 },
      "adjudicatedSuccessRate": 0,
      "evidenceCitationRate": 0.9375,
      "evidenceQualityRate": 0.229167,
      "providerTokens": 13416254,
      "providerTokenObservations": 47,
      "providerTokenCostUnits": 13416254,
      "latencyMeanMs": 68064.75,
      "latencyP95Ms": 124193,
      "totalCostUsd": null
    },
    {
      "scenarioId": "deterministic-doc-bridge",
      "observationCount": 48,
      "executionStatus": { "completed": 42, "budget-exceeded": 5, "timed-out": 1 },
      "completedRate": 0.875,
      "taskOutcome": { "success": 1, "partial": 29, "blocked": 17, "missing": 1 },
      "adjudicationOutcome": { "success": 0, "partial": 40, "blocked": 6, "incomplete": 2 },
      "adjudicatedSuccessRate": 0,
      "evidenceCitationRate": 0.9375,
      "evidenceQualityRate": 0.208333,
      "providerTokens": 11048857,
      "providerTokenObservations": 47,
      "providerTokenCostUnits": 11048857,
      "latencyMeanMs": 58335.292,
      "latencyP95Ms": 84440,
      "totalCostUsd": null
    }
  ],
  "pairedDeltas": {
    "comparisonDirection": "deterministic-doc-bridge minus repository-only",
    "providerTokenCostUnitsAverage": -53325.065,
    "providerTokenCostUnitsRelative": -0.18459,
    "providerTokenPairCount": 46,
    "latencyAverageMs": -9729.458,
    "latencyRelative": -0.142944,
    "latencyP95Ms": -39753,
    "completedRate": 0.125,
    "evidenceCitationRate": 0,
    "evidenceQualityRate": -0.020834,
    "adjudicatedSuccessRate": 0
  },
  "interpretation": {
    "classification": "inconclusive",
    "summary": "The deterministic Doc Bridge arm completed more executions and used fewer provider token-equivalent units with lower latency p95 in this controlled sample. Evidence citation was unchanged and high-quality evidence was slightly lower. The independent adjudicator found no successful outcome in either arm, so the study does not establish improved task correctness.",
    "decision": "Do not use this run as a causal, enterprise-readiness, or currency-cost claim. Use it as an auditable directional measurement and as input to the next study design."
  },
  "limitations": [
    "The cost metric is provider token-equivalent units, not USD; the CLI provider emitted no currency cost.",
    "Two observations lacked provider token counts, so paired token comparison uses 46 of 48 pairs.",
    "Adjudication is deterministic and bounded by execution status, acceptance metrics, and evidence count; it is not independent semantic review by a human or second model.",
    "The sample has 24 task definitions, two models, one replicate, and two scenarios; it does not establish causality or generalize to other repositories.",
    "The study task acceptance instrumentation produced no adjudicated successes; semantic correctness remains not analyzed."
  ],
  "contentHashAlgo": "sha256-normalized-v1",
  "contentHash": "9589b4e36283c36face82acdacbd756b3b96e001c59f2fb0574f9b5be4ef034c"
}