|
Download README.md from Haaardikkkk/bugagent-localizer: direct link, hf CLI and curl.
- Browser
- Download file 1.25 kB
-
https://huggingface.co/Haaardikkkk/bugagent-localizer/resolve/main/README.md
- Command line
-
hf download hf://Haaardikkkk/bugagent-localizer/README.md
-
curl -L -o README.md https://huggingface.co/Haaardikkkk/bugagent-localizer/resolve/main/README.md
1.25 kB
| license: apache-2.0 | |
| base_model: answerdotai/ModernBERT-base | |
| pipeline_tag: text-classification | |
| tags: [code, bug-detection, python, java, cpp] | |
| # BugAgent bug localizer | |
| A binary classifier (clean or buggy) over single functions in Python, Java and C/C++, used by | |
| [BugAgent](https://github.com/haaardikkk/BugAgent). Built on answerdotai/ModernBERT-base, with 512 tokens per function. | |
| ## Results | |
| AUC: 0.50 is chance and 1.00 is perfect. | |
| | Test | Held-out projects | Benchmarks never used in training or selection | | |
| |---|---|---| | |
| | Buggy vs its own fix | 0.49 | 0.50 | | |
| | Buggy vs fixed and unchanged code | 0.67 | 0.55 | | |
| | Buggy vs unchanged code | 0.75 | 0.58 | | |
| | Buggy ranked above its fix | 42% of pairs | 47% of pairs | | |
| **This model can't tell a bug from its own fix: that score is chance level.** BugAgent gives its scores zero weight | |
| when ranking problems. Don't rely on it to decide whether code is correct. | |
| ## Data | |
| Trained on: 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. | |
| Benchmarks: princeton-nlp/SWE-bench_Verified, ByteDance-Seed/Multi-SWE-bench. | |