bugagent-localizer / bugagent_meta.json
Haaardikkkk's picture
Upload BugAgent bug localizer
ef27391 verified
Raw History Blame Contribute Delete
3.4 kB
{
"format_version": 2,
"base_model": "answerdotai/ModernBERT-base",
"labels": [
"clean",
"buggy"
],
"clean_label": "clean",
"max_length": 512,
"languages": [
"python",
"java",
"cpp"
],
"normalization": {
"python": "ast_unparse_strip_docstrings_v1",
"java": "c_family_strip_comments_v1",
"cpp": "c_family_strip_comments_v1"
},
"objective": "binary classification (buggy vs unchanged) + pairwise ranking (buggy above its fix)",
"datasets": [
"nebius/SWE-rebench",
"princeton-nlp/SWE-bench (train)",
"nebius/SWE-bench-extra",
"SWE-Gym/SWE-Gym",
"ByteDance-Seed/Multi-SWE-RL",
"bigcode/commitpackft",
"ASSERT-KTH/megadiff-single-function",
"bstee615/bigvul"
],
"gold_test": [
"princeton-nlp/SWE-bench_Verified",
"ByteDance-Seed/Multi-SWE-bench"
],
"status": "final (metrics: held-out test projects)",
"metrics": {
"real_auc": 0.4935,
"pair_acc": 0.4221,
"clean_auc": 0.7545,
"bug_auc": 0.668,
"bug_f1": 0.5768,
"per_language": {
"python": {
"real_auc": 0.489,
"pair_acc": 0.4088,
"clean_auc": 0.7216,
"bug_auc": 0.6276,
"n_pairs": 5516,
"n_clean": 8133,
"bug_f1": 0.6007
},
"java": {
"real_auc": 0.4721,
"pair_acc": 0.3256,
"clean_auc": 0.8162,
"bug_auc": 0.7633,
"n_pairs": 129,
"n_clean": 709,
"bug_f1": 0.3673
},
"cpp": {
"real_auc": 0.5173,
"pair_acc": 0.5717,
"clean_auc": 0.7052,
"bug_auc": 0.6801,
"n_pairs": 572,
"n_clean": 3702,
"bug_f1": 0.4105
}
},
"gold_real_auc": 0.4971,
"gold_pair_acc": 0.4735
},
"trained_at": "2026-11-04T11:07:17Z",
"validation_metrics": {
"real_auc": 0.4941,
"pair_acc": 0.4197,
"clean_auc": 0.7916,
"bug_auc": 0.6859,
"bug_f1": 0.6451,
"per_language": {
"python": {
"real_auc": 0.491,
"pair_acc": 0.4167,
"clean_auc": 0.7366,
"bug_auc": 0.6138,
"n_pairs": 1500,
"n_clean": 1500,
"bug_f1": 0.6886
},
"java": {
"real_auc": 0.4761,
"pair_acc": 0.4071,
"clean_auc": 0.8034,
"bug_auc": 0.7524,
"n_pairs": 113,
"n_clean": 612,
"bug_f1": 0.3169
},
"cpp": {
"real_auc": 0.5306,
"pair_acc": 0.4884,
"clean_auc": 0.9166,
"bug_auc": 0.8852,
"n_pairs": 86,
"n_clean": 973,
"bug_f1": 0.4345
}
}
},
"gold_metrics": {
"all": {
"real_auc": 0.4971,
"pair_acc": 0.4735,
"clean_auc": 0.5773,
"bug_auc": 0.5467,
"n_pairs": 1491,
"n_clean": 2428,
"bug_f1": 0.4955
},
"python": {
"real_auc": 0.4822,
"pair_acc": 0.4045,
"clean_auc": 0.7194,
"bug_auc": 0.6311,
"n_pairs": 660,
"n_clean": 1114,
"bug_f1": 0.5937
},
"java": {
"real_auc": 0.4953,
"pair_acc": 0.4149,
"clean_auc": 0.7049,
"bug_auc": 0.6258,
"n_pairs": 188,
"n_clean": 310,
"bug_f1": 0.5371
},
"cpp": {
"real_auc": 0.5062,
"pair_acc": 0.5614,
"clean_auc": 0.4768,
"bug_auc": 0.4883,
"n_pairs": 643,
"n_clean": 1004,
"bug_f1": 0.3735
}
}
}