SWE-Gym (training set sample): every task, with its verdict
SWE-Gym, published by the SWE-Gym authors. Paper authors: Jiayi Pan, Xingyao Wang, Graham Neubig, Navdeep Jaitly, Heng Ji, Alane Suhr and Yizhe Zhang. SWE-Gym (arXiv) · This page covers a random 100-task sample of the 2,438 training tasks (SWE-Gym/SWE-Gym on Hugging Face). The sample is the 100 instance IDs with the lowest SHA-256 of "own1:swe-gym:<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 |
|---|---|---|
| pydantic__pydantic-5834 | no overlap found (rule check) | Numpy type annotations result in ValidatorIterator fields |
| pydantic__pydantic-8066 | no overlap found (rule check) | type casting does not work with multiple attributes of the same custom type |
| pydantic__pydantic-9001 | no overlap found (rule check) | field_serializer('*') |
| pydantic__pydantic-9053 | no overlap found (rule check) | Add support `re.Pattern[str]` to `pattern` field in `Field` |
| pydantic__pydantic-9170 | no overlap found (rule check) | Warn when `Field(alias=...)` is used as nested `Annotated` metadata |