{"url":"/task/test-driven-development","name":"test driven development","slug":"test-driven-development","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":24,"papers_with_code":8,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":8,"of":8,"tagged_in_all":24,"items":[{"url":"/paper/safety-and-performance-why-not-both-bi-1","title":"Safety and Performance, Why Not Both? Bi-Objective Optimized Model Compression against Heterogeneous Attacks Toward AI Software Deployment","date":"2024-01-02","arxiv_id":"2401.00996","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/safety-and-performance-why-not-both-bi","title":"Safety and Performance, Why not Both? Bi-Objective Optimized Model Compression toward AI Software Deployment","date":"2022-08-11","arxiv_id":"2208.05969","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/corecodebench-a-configurable-multi-scenario","title":"CoreCodeBench: A Configurable Multi-Scenario Repository-Level Benchmark","date":"2025-07-04","arxiv_id":"2507.05281","repositories_listed":1,"syntology":null},{"url":"/paper/swe-flow-synthesizing-software-engineering","title":"SWE-Flow: Synthesizing Software Engineering Data in a Test-Driven Manner","date":"2025-06-10","arxiv_id":"2506.09003","repositories_listed":1,"syntology":null},{"url":"/paper/otter-generating-tests-from-issues-to","title":"Otter: Generating Tests from Issues to Validate SWE Patches","date":"2025-02-07","arxiv_id":"2502.05368","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/tdd-bench-verified-can-llms-generate-tests","title":"TDD-Bench Verified: Can LLMs Generate Tests for Issues Before They Get Resolved?","date":"2024-12-03","arxiv_id":"2412.02883","repositories_listed":1,"syntology":null},{"url":"/paper/comprehensive-evaluation-and-insights-into-1","title":"Comprehensive Evaluation and Insights into the Use of Large Language Models in the Automation of Behavior-Driven Development Acceptance Test Formulation","date":"2024-03-22","arxiv_id":"2403.14965","repositories_listed":1,"syntology":null},{"url":"/paper/unit-test-case-generation-with-transformers","title":"Unit Test Case Generation with Transformers and Focal Context","date":"2020-09-11","arxiv_id":"2009.05617","repositories_listed":1,"syntology":null}],"syntology_records":3,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}