初始化项目，由ModelHub XC社区提供模型

Model: Zynerji/Ektome-Qwen2.5-Coder-7B-Instruct-PristinelyUncensored
Source: Original Platform

cert_Qwen2.5-Coder-7B-Instruct.json

@@ -0,0 +1,133 @@
+{
+  "sphragis_version": "0.1.0",
+  "generated_at": "2026-07-26T22:50:16.638557+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": 1205,
+        "ref_only": 5,
+        "cand_only": 6,
+        "both_wrong": 184
+      },
+      "acc_reference": 0.864286,
+      "acc_candidate": 0.865,
+      "regression_d": -0.000714,
+      "d_ci": [
+        -0.005714,
+        0.004286
+      ],
+      "d_upper_bound": 0.002857,
+      "p_regression": 0.72558594,
+      "p_regression_holm": 1.0,
+      "p_improvement": 0.5,
+      "improved": false,
+      "mde_at_power": 0.005886,
+      "n_needed_for_margin": 204,
+      "verdict": "PASS",
+      "reason": "non_inferior_within_margin"
+    },
+    {
+      "axis": "instruction",
+      "n": 600,
+      "counts": {
+        "both_correct": 394,
+        "ref_only": 4,
+        "cand_only": 2,
+        "both_wrong": 200
+      },
+      "acc_reference": 0.663333,
+      "acc_candidate": 0.66,
+      "regression_d": 0.003333,
+      "d_ci": [
+        -0.005,
+        0.011667
+      ],
+      "d_upper_bound": 0.01,
+      "p_regression": 0.34375,
+      "p_regression_holm": 1.0,
+      "p_improvement": 0.890625,
+      "improved": false,
+      "mde_at_power": 0.01,
+      "n_needed_for_margin": 204,
+      "verdict": "PASS",
+      "reason": "non_inferior_within_margin"
+    },
+    {
+      "axis": "knowledge",
+      "n": 400,
+      "counts": {
+        "both_correct": 387,
+        "ref_only": 0,
+        "cand_only": 0,
+        "both_wrong": 13
+      },
+      "acc_reference": 0.9675,
+      "acc_candidate": 0.9675,
+      "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": "reasoning",
+      "n": 400,
+      "counts": {
+        "both_correct": 381,
+        "ref_only": 0,
+        "cand_only": 0,
+        "both_wrong": 19
+      },
+      "acc_reference": 0.9525,
+      "acc_candidate": 0.9525,
+      "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"
+    }
+  ],
+  "params": {
+    "margin": 0.03,
+    "alpha": 0.05,
+    "n_floor": 30,
+    "power": 0.8,
+    "n_boot": 4000,
+    "seed": 0
+  }
+}