Add Neurips'26 and update datasets

README.md

@@ -4,6 +4,8 @@ license: mit
 
 # Precise Debugging Benchmarking (PDB)
 
+⭐ **Neurips'26: Evaluations & Datasets**
+
 📄 [Paper](https://arxiv.org/abs/2604.17338)  · 
 💻 [Code](https://github.com/Bill1235813/PDB)  · 
 🌐 [Project page](https://precise-debugging-benchmark.github.io/)  · 
@@ -24,21 +26,23 @@ frontier LLMs often fall back on.
 
 | Dataset | Size | Bug granularity | Notes |
 |---|---|---|---|
-| [PDB-Single](https://huggingface.co/datasets/Precise-Debugging-Benchmarking/PDB-Single) | 7,589 | single line | full initial pool before easy-case filtering |
-| [PDB-Single-Hard](https://huggingface.co/datasets/Precise-Debugging-Benchmarking/PDB-Single-Hard) | 5,751 | single line | hard subset: tasks not easily solved by 7+ of 9 reference models |
-| [PDB-Multi](https://huggingface.co/datasets/Precise-Debugging-Benchmarking/PDB-Multi) | 256 | 2–4 line blocks | multi-line extension on programs with ≥35 LOC; atomicity-filtered |
+| [PDB-Single](https://huggingface.co/datasets/Precise-Debugging-Benchmarking/PDB-Single) | 5,751 | single line | main evaluation set: tasks not easily solved by 7+ of 9 reference models |
+| [PDB-Single-Full](https://huggingface.co/datasets/Precise-Debugging-Benchmarking/PDB-Single-Full) | 7,589 | single line | full initial pool before easy-case filtering |
+| [PDB-Wild](https://huggingface.co/datasets/Precise-Debugging-Benchmarking/PDB-Wild) | 484 | multi-line / repository-level | PDB-Multi (256) + SWE-smith repository bugs (228) |
+| [PDB-Multi](https://huggingface.co/datasets/Precise-Debugging-Benchmarking/PDB-Multi) | 256 | 2–4 line blocks | BigCodeBench/LiveCodeBench part of PDB-Wild; programs with ≥35 LOC |
+| [PDB-Results](https://huggingface.co/datasets/Precise-Debugging-Benchmarking/PDB-Results) | – | – | model outputs and scores |
 
-All three are derived from [BigCodeBench](https://huggingface.co/datasets/bigcode/bigcodebench)
-and [LiveCodeBench](https://huggingface.co/datasets/livecodebench/execution),
-sourced via the PDB pipeline, and evaluated with precision / recall / unit-test
-pass rate.
+PDB-Single, PDB-Single-Full and PDB-Multi are derived from [BigCodeBench](https://huggingface.co/datasets/bigcode/bigcodebench)
+and [LiveCodeBench](https://huggingface.co/datasets/livecodebench/execution); PDB-Wild adds
+[SWE-smith](https://github.com/SWE-bench/SWE-smith) repositories. All are built by the PDB
+pipeline and evaluated with precision / recall / unit-test pass rate.
 
 ## Citation
 
 ```
-@article{zhu2026pdb,
+@article{chai2026pdb,
   title={Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?},
-  author={Zhu, Wang Bill and Chai, Miaosen and Wang, Shangshang and Liu, Yejia and Bian, Song and Dong, Honghua and Neiswanger, Willie and Jia, Robin},
+  author={Chai, Miaosen and Zhu, Wang Bill and Wang, Shangshang and Liu, Yejia and Bian, Song and Dong, Honghua and Neiswanger, Willie and Jia, Robin},
   journal={arXiv preprint arXiv:2604.17338},
   year={2026}
 }