Leaklens

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.

Download CSV
TaskVerdictIssue title
trinodb__trino-1584no overlap found (rule check)presto select query fails with permission denied for kerberized Hive metastore with hive metastore impersonation enabled.
trinodb__trino-2944no overlap found (rule check)New WebUI Authentication Manager Breaks Forwarded HTTPS
trinodb__trino-5010no overlap found (rule check)PrestoS3FileSystem should skip DeepArchive in addition to Glacier
trinodb__trino-725no overlap found (rule check)NullPointerException when local memory limits are exceeded