{
  "report_version": "1",
  "case_set": {
    "name": "inbox-triage",
    "sha256": "9b7392a423cd6595973591357ab12843404f9d8d69ef3b5b697aca6bc4bf1cf6"
  },
  "systems": [
    {
      "system": {
        "name": "model-triage-gemma4",
        "version": "1",
        "mode": "replay",
        "model": "gemma4:e2b@b37049369adf",
        "prompt": "triage-v1 sha256:053fdf51b21d891e",
        "tools": null
      },
      "recording_sha256": "5091cc6f4507bb6178eb49e30166904c48ff382d1e20b6894b1aabdea7557fb6",
      "trials_per_case": 10,
      "cases": 9,
      "verdicts": {
        "pass": 90
      },
      "not_run": 0,
      "failures_by_check": {},
      "incomplete_by_error": {},
      "per_case": {
        "charged-twice": {
          "class": "billing",
          "pass": 10,
          "fail": 0,
          "incomplete": 0,
          "not_run": 0
        },
        "stuck-tracking": {
          "class": "delivery",
          "pass": 10,
          "fail": 0,
          "incomplete": 0,
          "not_run": 0
        },
        "password-changed": {
          "class": "account security",
          "pass": 10,
          "fail": 0,
          "incomplete": 0,
          "not_run": 0
        },
        "product-advice": {
          "class": "out of scope",
          "pass": 10,
          "fail": 0,
          "incomplete": 0,
          "not_run": 0
        },
        "refund-missing": {
          "class": "billing",
          "pass": 10,
          "fail": 0,
          "incomplete": 0,
          "not_run": 0
        },
        "charged-after-closing": {
          "class": "billing, ambiguous wording",
          "pass": 10,
          "fail": 0,
          "incomplete": 0,
          "not_run": 0
        },
        "blank-message": {
          "class": "empty input",
          "pass": 10,
          "fail": 0,
          "incomplete": 0,
          "not_run": 0
        },
        "missing-body": {
          "class": "missing input",
          "pass": 10,
          "fail": 0,
          "incomplete": 0,
          "not_run": 0
        },
        "late-order": {
          "class": "delivery",
          "pass": 10,
          "fail": 0,
          "incomplete": 0,
          "not_run": 0
        }
      },
      "flaky_cases": [],
      "never_passed": [],
      "curve": {
        "1": {
          "pass_at_k": 1.0,
          "pass_power_k": 1.0
        },
        "2": {
          "pass_at_k": 1.0,
          "pass_power_k": 1.0
        },
        "3": {
          "pass_at_k": 1.0,
          "pass_power_k": 1.0
        },
        "4": {
          "pass_at_k": 1.0,
          "pass_power_k": 1.0
        },
        "5": {
          "pass_at_k": 1.0,
          "pass_power_k": 1.0
        },
        "6": {
          "pass_at_k": 1.0,
          "pass_power_k": 1.0
        },
        "7": {
          "pass_at_k": 1.0,
          "pass_power_k": 1.0
        },
        "8": {
          "pass_at_k": 1.0,
          "pass_power_k": 1.0
        },
        "9": {
          "pass_at_k": 1.0,
          "pass_power_k": 1.0
        },
        "10": {
          "pass_at_k": 1.0,
          "pass_power_k": 1.0
        }
      },
      "latency_s": {
        "trials": 70,
        "median": 0.651,
        "p90": 0.719
      }
    },
    {
      "system": {
        "name": "model-triage-qwen3.5",
        "version": "1",
        "mode": "replay",
        "model": "qwen3.5:0.8b@de63045f2975",
        "prompt": "triage-v1 sha256:053fdf51b21d891e",
        "tools": null
      },
      "recording_sha256": "b314b3dc5d1110821cfed88b21b39bc0212244e9eb5c3e6f51d695fc6fd38d6b",
      "trials_per_case": 10,
      "cases": 9,
      "verdicts": {
        "pass": 77,
        "fail": 13
      },
      "not_run": 0,
      "failures_by_check": {
        "failure-criteria": 2,
        "triage-outcome": 11
      },
      "incomplete_by_error": {},
      "per_case": {
        "charged-twice": {
          "class": "billing",
          "pass": 10,
          "fail": 0,
          "incomplete": 0,
          "not_run": 0
        },
        "stuck-tracking": {
          "class": "delivery",
          "pass": 10,
          "fail": 0,
          "incomplete": 0,
          "not_run": 0
        },
        "password-changed": {
          "class": "account security",
          "pass": 7,
          "fail": 3,
          "incomplete": 0,
          "not_run": 0
        },
        "product-advice": {
          "class": "out of scope",
          "pass": 2,
          "fail": 8,
          "incomplete": 0,
          "not_run": 0
        },
        "refund-missing": {
          "class": "billing",
          "pass": 10,
          "fail": 0,
          "incomplete": 0,
          "not_run": 0
        },
        "charged-after-closing": {
          "class": "billing, ambiguous wording",
          "pass": 10,
          "fail": 0,
          "incomplete": 0,
          "not_run": 0
        },
        "blank-message": {
          "class": "empty input",
          "pass": 10,
          "fail": 0,
          "incomplete": 0,
          "not_run": 0
        },
        "missing-body": {
          "class": "missing input",
          "pass": 10,
          "fail": 0,
          "incomplete": 0,
          "not_run": 0
        },
        "late-order": {
          "class": "delivery",
          "pass": 8,
          "fail": 2,
          "incomplete": 0,
          "not_run": 0
        }
      },
      "flaky_cases": [
        "password-changed",
        "product-advice",
        "late-order"
      ],
      "never_passed": [],
      "curve": {
        "1": {
          "pass_at_k": 0.8556,
          "pass_power_k": 0.8556
        },
        "2": {
          "pass_at_k": 0.921,
          "pass_power_k": 0.7901
        },
        "3": {
          "pass_at_k": 0.9472,
          "pass_power_k": 0.7509
        },
        "4": {
          "pass_at_k": 0.963,
          "pass_power_k": 0.7222
        },
        "5": {
          "pass_at_k": 0.9753,
          "pass_power_k": 0.7006
        },
        "6": {
          "pass_at_k": 0.9852,
          "pass_power_k": 0.6852
        },
        "7": {
          "pass_at_k": 0.9926,
          "pass_power_k": 0.675
        },
        "8": {
          "pass_at_k": 0.9975,
          "pass_power_k": 0.6691
        },
        "9": {
          "pass_at_k": 1.0,
          "pass_power_k": 0.6667
        },
        "10": {
          "pass_at_k": 1.0,
          "pass_power_k": 0.6667
        }
      },
      "latency_s": {
        "trials": 70,
        "median": 0.403,
        "p90": 0.462
      }
    }
  ]
}
