SWE-PolyBench (full set sample): every task, with its verdict
SWE-PolyBench, published by Amazon Science. Paper authors: Muhammad Shihab Rashid, Christian Bock, Yuan Zhuang, Alexander Buchholz, Tim Esler, Simon Valentin, Luca Franceschi, Martin Wistuba, Prabhu Teja Sivaprasad, Woo Jung Kim, Anoop Deoras, Giovanni Zappella and Laurent Callot. SWE-PolyBench (arXiv) · This page covers a random 100-task sample of the 2,110 tasks (AmazonScience/SWE-PolyBench on Hugging Face). The sample is the 100 instance IDs with the lowest SHA-256 of "own1:swe-polybench:<instance_id>", so anyone can redraw it. · Report a correction · flags show what the public text and git history contain: public exposure was possible, nothing more.
| Task | Verdict | Issue title |
|---|---|---|
| keras-team__keras-18553 | no overlap found (rule check) | depthwise_conv ops padding same is not working in on torch backend |
| keras-team__keras-19201 | no overlap found (rule check) | Typo in keras.distribution.initialize() |
| keras-team__keras-19484 | no overlap found (rule check) | keras adamw optimizer failed with callable parameters in TensorFlow2.16 |
| keras-team__keras-19973 | no overlap found (rule check) | Inconsistent assertion in keras.layers.MultiHeadAttention |