{
  "comparison_version": "1",
  "resamples": 2000,
  "seed": 20261020,
  "case_set": {
    "name": "inbox-triage-robustness",
    "sha256": "945fb939580c38abcadcd8df25534d2a51011800b00d7c0ed2c44587e0fa288c"
  },
  "trials": 5,
  "baseline": {
    "name": "model-triage-qwen3.5",
    "version": "v1",
    "mode": "replay",
    "model": "qwen3.5:0.8b@de63045f2975",
    "prompt": "triage-v1 sha256:053fdf51b21d891e",
    "tools": null,
    "index": null
  },
  "candidate": {
    "name": "model-triage-qwen3.5",
    "version": "v2",
    "mode": "replay",
    "model": "qwen3.5:0.8b@de63045f2975",
    "prompt": "triage-v2 sha256:d3ebc88d046c97b5",
    "tools": null,
    "index": null
  },
  "overall": {
    "cases": 44,
    "baseline": 0.85,
    "candidate": 0.8864,
    "difference": 0.0364,
    "interval_95": [
      0.0091,
      0.0682
    ],
    "better": 6,
    "worse": 0,
    "same": 38,
    "trial_level_interval_95": [
      0.0091,
      0.0636
    ],
    "source_groups": 9,
    "source_cluster_method": "exact over 24310 draws",
    "source_cluster_interval_95": [
      0.0,
      0.0727
    ],
    "source_no_gain_share": 0.026
  },
  "trial_pairs": {
    "both_pass": 186,
    "only_baseline": 1,
    "only_candidate": 9,
    "neither": 24
  },
  "slices": {
    "language": {
      "en": {
        "cases": 37,
        "baseline": 0.8595,
        "candidate": 0.8919,
        "difference": 0.0324,
        "interval_95": [
          0.0054,
          0.0649
        ],
        "better": 5,
        "worse": 0,
        "same": 32,
        "few_cases": false
      },
      "es": {
        "cases": 7,
        "baseline": 0.8,
        "candidate": 0.8571,
        "difference": 0.0571,
        "interval_95": [
          0.0,
          0.1714
        ],
        "better": 1,
        "worse": 0,
        "same": 6,
        "few_cases": true
      }
    },
    "variant": {
      "emphasis": {
        "cases": 7,
        "baseline": 0.8571,
        "candidate": 0.9143,
        "difference": 0.0571,
        "interval_95": [
          0.0,
          0.1714
        ],
        "better": 1,
        "worse": 0,
        "same": 6,
        "few_cases": true
      },
      "greeting": {
        "cases": 7,
        "baseline": 0.8571,
        "candidate": 0.8571,
        "difference": 0.0,
        "interval_95": [
          0.0,
          0.0
        ],
        "better": 0,
        "worse": 0,
        "same": 7,
        "few_cases": true
      },
      "original": {
        "cases": 9,
        "baseline": 0.8889,
        "candidate": 0.9333,
        "difference": 0.0444,
        "interval_95": [
          0.0,
          0.1111
        ],
        "better": 2,
        "worse": 0,
        "same": 7,
        "few_cases": true
      },
      "translation": {
        "cases": 7,
        "baseline": 0.8,
        "candidate": 0.8571,
        "difference": 0.0571,
        "interval_95": [
          0.0,
          0.1714
        ],
        "better": 1,
        "worse": 0,
        "same": 6,
        "few_cases": true
      },
      "typo": {
        "cases": 7,
        "baseline": 0.8286,
        "candidate": 0.8857,
        "difference": 0.0571,
        "interval_95": [
          0.0,
          0.1143
        ],
        "better": 2,
        "worse": 0,
        "same": 5,
        "few_cases": true
      },
      "uppercase": {
        "cases": 7,
        "baseline": 0.8571,
        "candidate": 0.8571,
        "difference": 0.0,
        "interval_95": [
          0.0,
          0.0
        ],
        "better": 0,
        "worse": 0,
        "same": 7,
        "few_cases": true
      }
    }
  },
  "cases": [
    {
      "case_id": "password-changed",
      "baseline": 0.8,
      "candidate": 1.0
    },
    {
      "case_id": "password-changed--typo",
      "baseline": 0.8,
      "candidate": 1.0
    },
    {
      "case_id": "product-advice",
      "baseline": 0.2,
      "candidate": 0.4
    },
    {
      "case_id": "product-advice--typo",
      "baseline": 0.0,
      "candidate": 0.2
    },
    {
      "case_id": "product-advice--emphasis",
      "baseline": 0.0,
      "candidate": 0.4
    },
    {
      "case_id": "charged-after-closing--es",
      "baseline": 0.6,
      "candidate": 1.0
    }
  ]
}
