PabJev-4b / reference_results /package_validation /package_vs_reference.json
roudone's picture
Upload PabJev-4b (qwen3.5 4b base, short150 best step-150 decision model)
2a4e414 verified
Raw History Blame Contribute Delete
3.78 kB
{
"candidate_summary": {
"accuracy": 0.883117,
"per_type_accuracy": {
"choice": 0.892086,
"noul": 0.864865,
"score": 0.888889
},
"intelligence": 51.3356,
"calibration": 90.7539,
"ece": 0.071062,
"fidelity": 0.886139
},
"reference_summary": {
"accuracy": 0.883117,
"per_type_accuracy": {
"choice": 0.892086,
"noul": 0.864865,
"score": 0.888889
},
"intelligence": 51.3356,
"calibration": 90.7539,
"ece": 0.071062,
"fidelity": 0.886139
},
"n_candidate": 231,
"n_reference": 231,
"n_common": 231,
"missing_in_candidate": [],
"missing_in_reference": [],
"n_label_mismatch": 0,
"label_mismatches": [],
"n_probability_shape_mismatch": 0,
"probability_shape_mismatches": [],
"probability_max_abs": 0.0,
"probability_mean_of_row_mean_abs": 0.0,
"probability_mean_of_row_max_abs": 0.0,
"largest_drifts": [
{
"id": "easy-extraction-00",
"max_abs": 0.0,
"mean_abs": 0.0,
"candidate_pred": 3,
"reference_pred": 3
},
{
"id": "easy-extraction-01",
"max_abs": 0.0,
"mean_abs": 0.0,
"candidate_pred": 1,
"reference_pred": 1
},
{
"id": "easy-extraction-02",
"max_abs": 0.0,
"mean_abs": 0.0,
"candidate_pred": 0,
"reference_pred": 0
},
{
"id": "easy-extraction-03",
"max_abs": 0.0,
"mean_abs": 0.0,
"candidate_pred": 0,
"reference_pred": 0
},
{
"id": "easy-extraction-04",
"max_abs": 0.0,
"mean_abs": 0.0,
"candidate_pred": 1,
"reference_pred": 1
},
{
"id": "easy-extraction-05",
"max_abs": 0.0,
"mean_abs": 0.0,
"candidate_pred": 3,
"reference_pred": 3
},
{
"id": "easy-extraction-06",
"max_abs": 0.0,
"mean_abs": 0.0,
"candidate_pred": 1,
"reference_pred": 1
},
{
"id": "easy-extraction-07",
"max_abs": 0.0,
"mean_abs": 0.0,
"candidate_pred": 3,
"reference_pred": 3
},
{
"id": "easy-extraction-08",
"max_abs": 0.0,
"mean_abs": 0.0,
"candidate_pred": 2,
"reference_pred": 2
},
{
"id": "easy-extraction-09",
"max_abs": 0.0,
"mean_abs": 0.0,
"candidate_pred": 1,
"reference_pred": 1
},
{
"id": "easy-extraction-10",
"max_abs": 0.0,
"mean_abs": 0.0,
"candidate_pred": 0,
"reference_pred": 0
},
{
"id": "easy-extraction-11",
"max_abs": 0.0,
"mean_abs": 0.0,
"candidate_pred": 2,
"reference_pred": 2
},
{
"id": "easy-fact-00",
"max_abs": 0.0,
"mean_abs": 0.0,
"candidate_pred": 1,
"reference_pred": 1
},
{
"id": "easy-fact-01",
"max_abs": 0.0,
"mean_abs": 0.0,
"candidate_pred": 0,
"reference_pred": 0
},
{
"id": "easy-fact-02",
"max_abs": 0.0,
"mean_abs": 0.0,
"candidate_pred": 1,
"reference_pred": 1
},
{
"id": "easy-fact-03",
"max_abs": 0.0,
"mean_abs": 0.0,
"candidate_pred": 0,
"reference_pred": 0
},
{
"id": "easy-fact-04",
"max_abs": 0.0,
"mean_abs": 0.0,
"candidate_pred": 1,
"reference_pred": 1
},
{
"id": "easy-fact-05",
"max_abs": 0.0,
"mean_abs": 0.0,
"candidate_pred": 0,
"reference_pred": 0
},
{
"id": "easy-fact-06",
"max_abs": 0.0,
"mean_abs": 0.0,
"candidate_pred": 1,
"reference_pred": 1
},
{
"id": "easy-fact-07",
"max_abs": 0.0,
"mean_abs": 0.0,
"candidate_pred": 0,
"reference_pred": 0
}
]
}