{ "@context": { "@language": "en", "@vocab": "https://schema.org/", "citeAs": "cr:citeAs", "column": "cr:column", "conformsTo": "dct:conformsTo", "cr": "http://mlcommons.org/croissant/", "data": { "@id": "cr:data", "@type": "@json" }, "dataBiases": "cr:dataBiases", "dataCollection": "cr:dataCollection", "dataType": { "@id": "cr:dataType", "@type": "@vocab" }, "dct": "http://purl.org/dc/terms/", "extract": "cr:extract", "field": "cr:field", "fileProperty": "cr:fileProperty", "fileObject": "cr:fileObject", "fileSet": "cr:fileSet", "format": "cr:format", "includes": "cr:includes", "isLiveDataset": "cr:isLiveDataset", "jsonPath": "cr:jsonPath", "key": "cr:key", "md5": "cr:md5", "parentField": "cr:parentField", "path": "cr:path", "personalSensitiveInformation": "cr:personalSensitiveInformation", "recordSet": "cr:recordSet", "references": "cr:references", "regex": "cr:regex", "repeated": "cr:repeated", "replace": "cr:replace", "sc": "https://schema.org/", "separator": "cr:separator", "source": "cr:source", "subField": "cr:subField", "transform": "cr:transform" }, "@type": "sc:Dataset", "@id": "https://lateos.ai/categories/datasets/polypatch/", "conformsTo": "http://mlcommons.org/croissant/1.0", "name": "PolyPatch-11k", "description": "A corpus of 11,611 real-world GitHub issue-and-patch instances mined from 3,886 repositories across 7 programming languages. Each instance pairs an issue description with the test changes that define the task and the test ids those changes touch. Training and mining corpus, NOT an execution-verified benchmark: fail_to_pass ids are derived statically and no test was executed. The gold solution patch is deliberately withheld.", "version": "2.0.0", "license": "https://opensource.org/licenses/MIT", "url": "https://lateos.ai/categories/datasets/polypatch/", "isLiveDataset": false, "personalSensitiveInformation": "None known. All content originates from public GitHub repositories; author names may appear incidentally inside diffs and issue text.", "dataCollection": "Mined from public GitHub pull requests, deduplicated on instance_id, structurally validated, and split so that no repository appears in both train and test.", "dataBiases": "Heavily skewed toward Python (8,399 of 11,611 instances). C++ (70), PHP (63), JavaScript (31) and Java (24) are thinly represented. CI workflow metadata is present on only 23.1% of instances. Test ids are derived by static attribution and have not been validated by execution.", "citeAs": "@article{xu2025swingarena, title={SwingArena: Competitive Programming Arena for Long-context GitHub Issue Solving}, author={Xu, Wendong and Xiong, Jing and Zhao, Chenyang and Chen, Qiujiang and Wang, Haoran and Shen, Hui and Wan, Zhongwei and Dai, Jianbo and Wu, Taiqiang and Xiao, He and others}, journal={arXiv preprint arXiv:2505.23932}, year={2025}}", "creator": { "@type": "sc:Organization", "name": "Lateos", "url": "https://lateos.ai" }, "keywords": [ "software engineering", "issue resolution", "program repair", "code patches", "multilingual", "unit tests", "continuous integration" ], "distribution": [ { "@type": "cr:FileObject", "@id": "polypatch-bulk", "name": "polypatch-11k-v2.jsonl.zst", "description": "All 11,611 gold instances as zstd-compressed JSON Lines, one instance per line, at full field length.", "contentUrl": "https://polypatch.lateos.ai/v1/bulk", "encodingFormat": "application/jsonlines+zstd", "sha256": "41e95bc912b61e30ef05777e429e02cb9bce9f34ea9f6de8d63147e1ca0a251d" } ], "recordSet": [ { "@type": "cr:RecordSet", "@id": "instances", "name": "instances", "description": "One record per benchmark task instance. The gold solution patch is not included.", "key": { "@id": "instances/instance_id" }, "field": [ { "@type": "cr:Field", "@id": "instances/instance_id", "name": "instance_id", "description": "Stable identifier, formatted __-.", "dataType": "sc:Text", "source": { "fileObject": { "@id": "polypatch-bulk" }, "extract": { "jsonPath": "$.instance_id" } } }, { "@type": "cr:Field", "@id": "instances/repo", "name": "repo", "description": "Source GitHub repository, owner/name.", "dataType": "sc:Text", "source": { "fileObject": { "@id": "polypatch-bulk" }, "extract": { "jsonPath": "$.repo" } } }, { "@type": "cr:Field", "@id": "instances/base_commit", "name": "base_commit", "description": "Commit the task is based on (40-hex SHA).", "dataType": "sc:Text", "source": { "fileObject": { "@id": "polypatch-bulk" }, "extract": { "jsonPath": "$.base_commit" } } }, { "@type": "cr:Field", "@id": "instances/language", "name": "language", "description": "One of python, rust, go, cpp, php, java, javascript.", "dataType": "sc:Text", "source": { "fileObject": { "@id": "polypatch-bulk" }, "extract": { "jsonPath": "$.language" } } }, { "@type": "cr:Field", "@id": "instances/problem_statement", "name": "problem_statement", "description": "The issue text describing what needs fixing.", "dataType": "sc:Text", "source": { "fileObject": { "@id": "polypatch-bulk" }, "extract": { "jsonPath": "$.problem_statement" } } }, { "@type": "cr:Field", "@id": "instances/test_patch", "name": "test_patch", "description": "Unified diff of the test changes that define the task.", "dataType": "sc:Text", "source": { "fileObject": { "@id": "polypatch-bulk" }, "extract": { "jsonPath": "$.test_patch" } } }, { "@type": "cr:Field", "@id": "instances/fail_to_pass", "name": "fail_to_pass", "description": "Test ids attributed to the test patch. STATICALLY DERIVED, NOT EXECUTION-VERIFIED.", "dataType": "sc:Text", "repeated": true, "source": { "fileObject": { "@id": "polypatch-bulk" }, "extract": { "jsonPath": "$.fail_to_pass[*]" } } }, { "@type": "cr:Field", "@id": "instances/test_count", "name": "test_count", "description": "Number of attributed test ids (1-20).", "dataType": "sc:Integer", "source": { "fileObject": { "@id": "polypatch-bulk" }, "extract": { "jsonPath": "$.test_count" } } }, { "@type": "cr:Field", "@id": "instances/ci_name_list", "name": "ci_name_list", "description": "CI workflow paths for the repository. Present on 23.1% of instances.", "dataType": "sc:Text", "repeated": true, "source": { "fileObject": { "@id": "polypatch-bulk" }, "extract": { "jsonPath": "$.ci_name_list[*]" } } }, { "@type": "cr:Field", "@id": "instances/ci_annotated", "name": "ci_annotated", "description": "True when ci_name_list is non-empty.", "dataType": "sc:Boolean", "source": { "fileObject": { "@id": "polypatch-bulk" }, "extract": { "jsonPath": "$.ci_annotated" } } }, { "@type": "cr:Field", "@id": "instances/source_url", "name": "source_url", "description": "Originating GitHub commit. Resolves for all 11,611 instances.", "dataType": "sc:URL", "source": { "fileObject": { "@id": "polypatch-bulk" }, "extract": { "jsonPath": "$.provenance.source_url" } } }, { "@type": "cr:Field", "@id": "instances/content_hash", "name": "content_hash", "description": "SHA-256 over the canonical task fields.", "dataType": "sc:Text", "source": { "fileObject": { "@id": "polypatch-bulk" }, "extract": { "jsonPath": "$.provenance.content_hash" } } } ] } ] }