iHore/SWE-bench_Pro
8
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Jeff Da
2025-09-19 18:21:28 +00:00
committed by system
parent 59332d9bad
commit c39ba5c30f
1 changed files with 2 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+2 -21
View File
@@ -49,26 +49,7 @@ See the related evaluation Github: https://github.com/scaleapi/SWE-bench_Pro-os
## Dataset Structure
### Data Instances
An example datum contains:
```json
{
"repo": "repository_name",
"instance_id": "unique_identifier_65_to_120_chars",
"base_commit": "40_char_git_commit_hash",
"patch": "code_patch_diff_1.44k_to_180k_chars",
"test_patch": "test_cases_325_to_322k_chars",
"problem_statement": "issue_description_419_to_8.04k_chars",
"requirements": "project_dependencies_124_to_6.7k_chars",
"interface": "api_specifications_1_to_12.2k_chars",
"repo_language": "programming_language",
"fail_to_pass": "tests_that_should_pass_after_patch_10_to_155k_chars",
"pass_to_pass": "tests_that_should_continue_passing_2_to_532k_chars",
"issue_specificity": "specificity_level_12_to_77_chars",
"issue_categories": "issue_type_categories_and_tags"
}
```
We follow SWE-Bench Verified (https://huggingface.co/datasets/SWE-bench/SWE-bench_Verified) in terms of dataset structure, with several extra fields.
## Data Fields
@@ -78,7 +59,7 @@ instance_id (string): Unique identifier for each instance (65-120 characters)
base_commit (string): Git commit hash of the base version (40 characters)
patch (string): The actual code patch/diff (1.44k - 180k characters)
patch (string): The golden code patch/diff (1.44k - 180k characters)
test_patch (string): Test cases related to the patch (325 - 322k characters)