{
  "sphragis_version": "0.1.0",
  "generated_at": "2026-07-27T03:53:12.900485+00:00",
  "reference": {
    "endpoint": "http://127.0.0.1:8080/v1",
    "model": "ref"
  },
  "candidate": {
    "endpoint": "http://127.0.0.1:8081/v1",
    "model": "cand"
  },
  "pack": {
    "name": "/root/pack_v2.jsonl",
    "n_tasks": 2800,
    "sha256": "2de27099bbb15bab4f7b35599b215f038fdb68b3f5f4e1cda1a464f9dd18e14e"
  },
  "overall": "PASS",
  "claim": "For every axis, the candidate was demonstrated non-inferior to the reference: the one-sided 95% upper confidence bound on the accuracy regression is below the margin of 3.0%.",
  "axes": [
    {
      "axis": "arithmetic",
      "n": 1400,
      "counts": {
        "both_correct": 1301,
        "ref_only": 4,
        "cand_only": 1,
        "both_wrong": 94
      },
      "acc_reference": 0.932143,
      "acc_candidate": 0.93,
      "regression_d": 0.002143,
      "d_ci": [
        -0.000714,
        0.005714
      ],
      "d_upper_bound": 0.005,
      "p_regression": 0.1875,
      "p_regression_holm": 0.75,
      "p_improvement": 0.96875,
      "improved": false,
      "mde_at_power": 0.003571,
      "n_needed_for_margin": 204,
      "verdict": "PASS",
      "reason": "non_inferior_within_margin"
    },
    {
      "axis": "instruction",
      "n": 600,
      "counts": {
        "both_correct": 454,
        "ref_only": 0,
        "cand_only": 0,
        "both_wrong": 146
      },
      "acc_reference": 0.756667,
      "acc_candidate": 0.756667,
      "regression_d": 0.0,
      "d_ci": [
        0.0,
        0.0
      ],
      "d_upper_bound": 0.0,
      "p_regression": 1.0,
      "p_regression_holm": 1.0,
      "p_improvement": 1.0,
      "improved": false,
      "mde_at_power": null,
      "n_needed_for_margin": 204,
      "verdict": "PASS",
      "reason": "non_inferior_within_margin"
    },
    {
      "axis": "knowledge",
      "n": 400,
      "counts": {
        "both_correct": 380,
        "ref_only": 7,
        "cand_only": 9,
        "both_wrong": 4
      },
      "acc_reference": 0.9675,
      "acc_candidate": 0.9725,
      "regression_d": -0.005,
      "d_ci": [
        -0.025,
        0.015
      ],
      "d_upper_bound": 0.01,
      "p_regression": 0.77275085,
      "p_regression_holm": 1.0,
      "p_improvement": 0.40180969,
      "improved": false,
      "mde_at_power": 0.0248,
      "n_needed_for_margin": 273,
      "verdict": "PASS",
      "reason": "non_inferior_within_margin"
    },
    {
      "axis": "reasoning",
      "n": 400,
      "counts": {
        "both_correct": 371,
        "ref_only": 0,
        "cand_only": 2,
        "both_wrong": 27
      },
      "acc_reference": 0.9275,
      "acc_candidate": 0.9325,
      "regression_d": -0.005,
      "d_ci": [
        -0.0125,
        0.0
      ],
      "d_upper_bound": 0.0,
      "p_regression": 1.0,
      "p_regression_holm": 1.0,
      "p_improvement": 0.25,
      "improved": false,
      "mde_at_power": 0.005,
      "n_needed_for_margin": 204,
      "verdict": "PASS",
      "reason": "non_inferior_within_margin"
    }
  ],
  "params": {
    "margin": 0.03,
    "alpha": 0.05,
    "n_floor": 30,
    "power": 0.8,
    "n_boot": 4000,
    "seed": 0
  }
}