{
  "schema": "qorx.evaluation.v1",
  "generated_at": "2026-05-03T12:34:00+00:00",
  "suite": "live",
  "target_path": ".",
  "git_commit": "b838c23",
  "qorx_version": "qorx 1.0.4-a.0",
  "budget_tokens": 600,
  "squeeze_budget_tokens": 450,
  "queries": [
    "context fault proof pages resolver boundary",
    "qorx carriers .qorx .qorxb qorx handle",
    "strict answer refusal unsupported claims"
  ],
  "supported_question": "context fault proof pages resolver boundary",
  "unsupported_question": "galactic banana escrow treaty",
  "agent_objective": "prove context fault proof pages resolver boundary",
  "output_json": "docs/benchmarks/live.json",
  "output_md": "docs/benchmarks/live.md",
  "summary": {
    "indexed_tokens": 202986,
    "strict_tasks": 2,
    "strict_task_passes": 2,
    "strict_task_pass_rate": 1.0,
    "expected_refusals": 1,
    "expected_refusal_passes": 1,
    "expected_refusal_pass_rate": 1.0,
    "agent_provider_calls": 0,
    "note": "Local benchmark. Token counts are Qorx deterministic estimates, not provider billing records."
  },
  "session": {
    "json": {
      "quark_count": 380,
      "indexed_tokens": 202986,
      "visible_tokens": 69,
      "omitted_tokens": 202917,
      "context_reduction_x": 2941.8260869565215
    }
  },
  "pack": {
    "json": {
      "used_tokens": 484,
      "omitted_tokens": 202502,
      "context_reduction_x": 419.39256198347107,
      "quarks_used": 3
    }
  },
  "squeeze": {
    "json": {
      "used_tokens": 419,
      "omitted_tokens": 202567,
      "context_reduction_x": 484.45346062052505,
      "quarks_used": 3
    }
  },
  "bench": {
    "json": {
      "average_reduction_x": 400.59937140587385,
      "rows": [
        {
          "query": "context fault proof pages resolver boundary",
          "used_tokens": 484,
          "omitted_tokens": 202502,
          "context_reduction_x": 419.39256198347107,
          "quarks_used": 3
        },
        {
          "query": "qorx carriers .qorx .qorxb qorx handle",
          "used_tokens": 511,
          "omitted_tokens": 202475,
          "context_reduction_x": 397.2328767123288,
          "quarks_used": 3
        },
        {
          "query": "strict answer refusal unsupported claims",
          "used_tokens": 527,
          "omitted_tokens": 202459,
          "context_reduction_x": 385.17267552182165,
          "quarks_used": 4
        }
      ]
    }
  },
  "agent": {
    "json": {
      "provider_calls": 0,
      "local_only": true
    }
  },
  "strict_answer_tasks": [
    {
      "question": "context fault proof pages resolver boundary",
      "expected_coverage": "supported",
      "actual_coverage": "supported",
      "passed": true,
      "evidence_count": 3,
      "used_tokens": 380
    },
    {
      "question": "galactic banana escrow treaty",
      "expected_coverage": "not_found",
      "actual_coverage": "not_found",
      "passed": true,
      "evidence_count": 0,
      "used_tokens": 8
    }
  ],
  "reproduce_command": "python scripts/run-benchmark.py --target . --suite live --budget-tokens 600 --squeeze-budget-tokens 450 --query \"context fault proof pages resolver boundary\" --query \"qorx carriers .qorx .qorxb qorx handle\" --query \"strict answer refusal unsupported claims\" --supported-question \"context fault proof pages resolver boundary\" --unsupported-question \"galactic banana escrow treaty\" --agent-objective \"prove context fault proof pages resolver boundary\" --output-json docs/benchmarks/live.json --output-md docs/benchmarks/live.md"
}
