{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/repost-scalable-repository-level-coding","title":"RepoST: Scalable Repository-Level Coding Environment Construction with Sandbox Testing","arxiv_id":"2503.07358","date":"2025-03-10","proceeding":null,"authors":["Yiqing Xie","Alex Xie","Divyanshu Sheth","PengFei Liu","Daniel Fried","Carolyn Rose"],"abstract":"We present RepoST, a scalable method to construct environments that provide execution feedback for repository-level code generation for both training and evaluation. Unlike existing works that aim to build entire repositories for execution, which is challenging for both human and LLMs, we provide execution feedback with sandbox testing, which isolates a given target function and its dependencies to a separate script for testing. Sandbox testing reduces the complexity of external dependencies and enables constructing environments at a large scale. We use our method to construct RepoST-Train, a large-scale train set with 7,415 functions from 832 repositories. Training with the execution feedback provided by RepoST-Train leads to a performance gain of 5.5% Pass@1 on HumanEval and 3.5% Pass@1 on RepoEval. We also build an evaluation dataset, RepoST-Eval, and benchmark 12 code generation models.","url_abs":"https://arxiv.org/abs/2503.07358v1","url_pdf":"https://arxiv.org/pdf/2503.07358v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"repost-scalable-repository-level-coding","repo_url":"https://github.com/yiqingxyq/RepoST","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"code-generation","task_name":"Code Generation"},{"task_slug":"humaneval","task_name":"HumanEval"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.07358","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.07358"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yiqingxyq/RepoST","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":18},"by_repo_kind":{"official":{"samples":18,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"03643c3e849d1895","entry":"direct_return","repo":"yiqingxyq/RepoST","repo_kind":"official","path":"utils_exec.py","file_url":"https://github.com/yiqingxyq/RepoST/blob/HEAD/utils_exec.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"03643c3e849d1895"}},{"code_sha256_prefix":"34dcaa09d95a53cd","entry":"extract_answer","repo":"yiqingxyq/RepoST","repo_kind":"official","path":"RepoST/llm_check.py","file_url":"https://github.com/yiqingxyq/RepoST/blob/HEAD/RepoST/llm_check.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"34dcaa09d95a53cd"}},{"code_sha256_prefix":"71210ee33ca4b9bb","entry":"extract_code","repo":"yiqingxyq/RepoST","repo_kind":"official","path":"utils.py","file_url":"https://github.com/yiqingxyq/RepoST/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"71210ee33ca4b9bb"}},{"code_sha256_prefix":"839e07f1bf52b601","entry":"get_chunks","repo":"yiqingxyq/RepoST","repo_kind":"official","path":"CodeRAGBench_evaluation/chunk.py","file_url":"https://github.com/yiqingxyq/RepoST/blob/HEAD/CodeRAGBench_evaluation/chunk.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"839e07f1bf52b601"}},{"code_sha256_prefix":"7a28ae5a90bb29be","entry":"get_code_block_by_path","repo":"yiqingxyq/RepoST","repo_kind":"official","path":"RepoST/sandboxing.py","file_url":"https://github.com/yiqingxyq/RepoST/blob/HEAD/RepoST/sandboxing.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7a28ae5a90bb29be"}},{"code_sha256_prefix":"b029cfa4ea645270","entry":"insert_gt_implementation","repo":"yiqingxyq/RepoST","repo_kind":"official","path":"RepoST/execution.py","file_url":"https://github.com/yiqingxyq/RepoST/blob/HEAD/RepoST/execution.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b029cfa4ea645270"}},{"code_sha256_prefix":"e0ec2aae48ea0c51","entry":"limit_virtual_memory","repo":"yiqingxyq/RepoST","repo_kind":"official","path":"utils_exec.py","file_url":"https://github.com/yiqingxyq/RepoST/blob/HEAD/utils_exec.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e0ec2aae48ea0c51"}},{"code_sha256_prefix":"f9144be15f4f516e","entry":"list_files","repo":"yiqingxyq/RepoST","repo_kind":"official","path":"utils.py","file_url":"https://github.com/yiqingxyq/RepoST/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f9144be15f4f516e"}},{"code_sha256_prefix":"83a52f31a2151a62","entry":"make_code_block_str","repo":"yiqingxyq/RepoST","repo_kind":"official","path":"RepoST/improve_coverage.py","file_url":"https://github.com/yiqingxyq/RepoST/blob/HEAD/RepoST/improve_coverage.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"83a52f31a2151a62"}},{"code_sha256_prefix":"82c2cd331aa5fd1f","entry":"reindent_func","repo":"yiqingxyq/RepoST","repo_kind":"official","path":"RepoST/improve_coverage.py","file_url":"https://github.com/yiqingxyq/RepoST/blob/HEAD/RepoST/improve_coverage.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"82c2cd331aa5fd1f"}},{"code_sha256_prefix":"41ba2522b7581d57","entry":"replace_test_function","repo":"yiqingxyq/RepoST","repo_kind":"official","path":"RepoST/improve_coverage.py","file_url":"https://github.com/yiqingxyq/RepoST/blob/HEAD/RepoST/improve_coverage.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"41ba2522b7581d57"}},{"code_sha256_prefix":"1fde51e64cde49da","entry":"run_program","repo":"yiqingxyq/RepoST","repo_kind":"official","path":"utils_exec.py","file_url":"https://github.com/yiqingxyq/RepoST/blob/HEAD/utils_exec.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1fde51e64cde49da"}},{"code_sha256_prefix":"059a4f9c0b756eac","entry":"safe_parse","repo":"yiqingxyq/RepoST","repo_kind":"official","path":"utils.py","file_url":"https://github.com/yiqingxyq/RepoST/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"059a4f9c0b756eac"}},{"code_sha256_prefix":"a7905fec7f88bb69","entry":"sanity_check","repo":"yiqingxyq/RepoST","repo_kind":"official","path":"RepoST/debug.py","file_url":"https://github.com/yiqingxyq/RepoST/blob/HEAD/RepoST/debug.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a7905fec7f88bb69"}},{"code_sha256_prefix":"dda16da5d86b85db","entry":"sanity_check","repo":"yiqingxyq/RepoST","repo_kind":"official","path":"RepoST/sandboxing.py","file_url":"https://github.com/yiqingxyq/RepoST/blob/HEAD/RepoST/sandboxing.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dda16da5d86b85db"}},{"code_sha256_prefix":"94b750b73f312f6a","entry":"skip_non_target_functions","repo":"yiqingxyq/RepoST","repo_kind":"official","path":"RepoST/execution.py","file_url":"https://github.com/yiqingxyq/RepoST/blob/HEAD/RepoST/execution.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"94b750b73f312f6a"}},{"code_sha256_prefix":"5dbae161e828ae94","entry":"truncate_documentation","repo":"yiqingxyq/RepoST","repo_kind":"official","path":"CodeRAGBench_evaluation/chunk.py","file_url":"https://github.com/yiqingxyq/RepoST/blob/HEAD/CodeRAGBench_evaluation/chunk.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5dbae161e828ae94"}},{"code_sha256_prefix":"efd84bdfa4cd0bb2","entry":"truncate_text","repo":"yiqingxyq/RepoST","repo_kind":"official","path":"CodeRAGBench_evaluation/chunk.py","file_url":"https://github.com/yiqingxyq/RepoST/blob/HEAD/CodeRAGBench_evaluation/chunk.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"efd84bdfa4cd0bb2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}