133 lines
3.1 KiB
JSON
133 lines
3.1 KiB
JSON
{
|
|
"sphragis_version": "0.1.0",
|
|
"generated_at": "2026-07-27T17:59:04.397198+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": 0,
|
|
"ref_only": 0,
|
|
"cand_only": 0,
|
|
"both_wrong": 1400
|
|
},
|
|
"acc_reference": 0.0,
|
|
"acc_candidate": 0.0,
|
|
"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": "instruction",
|
|
"n": 600,
|
|
"counts": {
|
|
"both_correct": 0,
|
|
"ref_only": 0,
|
|
"cand_only": 0,
|
|
"both_wrong": 600
|
|
},
|
|
"acc_reference": 0.0,
|
|
"acc_candidate": 0.0,
|
|
"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": 0,
|
|
"ref_only": 0,
|
|
"cand_only": 0,
|
|
"both_wrong": 400
|
|
},
|
|
"acc_reference": 0.0,
|
|
"acc_candidate": 0.0,
|
|
"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": 0,
|
|
"ref_only": 0,
|
|
"cand_only": 0,
|
|
"both_wrong": 400
|
|
},
|
|
"acc_reference": 0.0,
|
|
"acc_candidate": 0.0,
|
|
"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
|
|
}
|
|
} |