{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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 (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":24,"of":24,"of_with_code":8,"tagged_in_all":24,"counts":{"archive_papers_tagged":24,"with_a_code_link":8,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":24,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":2,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/safety-and-performance-why-not-both-bi-1","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/safety-and-performance-why-not-both-bi-1#ran","syntology_url":"https://syntology.ai/paper/2401.00996","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.00996"}},"official":{"repos":["jiepku/safecompress"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/safety-and-performance-why-not-both-bi","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/safety-and-performance-why-not-both-bi#ran","syntology_url":"https://syntology.ai/paper/2208.05969","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.05969"}},"official":{"repos":["jiepku/mia-safecompress"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/corecodebench-a-configurable-multi-scenario","slug":"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","slug":"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","slug":"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_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/otter-generating-tests-from-issues-to#ran","syntology_url":"https://syntology.ai/paper/2502.05368","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.05368"}},"official":{"repos":["IBM/TDD-Bench-Verified"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tdd-bench-verified-can-llms-generate-tests","slug":"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","slug":"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","slug":"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},{"url":null,"slug":"use-property-based-testing-to-bridge-llm-code","title":"Use Property-Based Testing to Bridge LLM Code Generation and Validation","date":"2025-06-23","arxiv_id":"2506.18315","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-automotive-code-large-language","title":"Generating Automotive Code: Large Language Models for Software Development and Verification in Safety-Critical Systems","date":"2025-06-04","arxiv_id":"2506.04038","repositories_listed":0,"syntology":null},{"url":null,"slug":"tests-as-prompt-a-test-driven-development","title":"Tests as Prompt: A Test-Driven-Development Benchmark for LLM Code Generation","date":"2025-05-13","arxiv_id":"2505.09027","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-defects-to-demands-a-unified-iterative","title":"From Defects to Demands: A Unified, Iterative, and Heuristically Guided LLM-Based Framework for Automated Software Repair and Requirement Realization","date":"2024-12-06","arxiv_id":"2412.05098","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-source-evolutionary-computation-with","title":"Open Source Evolutionary Computation with Chips-n-Salsa","date":"2024-12-02","arxiv_id":"2412.02004","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-evaluation-driven-approach-to-designing","title":"Evaluation-Driven Development of LLM Agents: A Process Model and Reference Architecture","date":"2024-11-21","arxiv_id":"2411.13768","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparative-study-on-the-impact-of-test","title":"A Comparative Study on the Impact of Test-Driven Development (TDD) and Behavior-Driven Development (BDD) on Enterprise Software Delivery Effectiveness","date":"2024-11-05","arxiv_id":"2411.04141","repositories_listed":0,"syntology":null},{"url":null,"slug":"test-driven-development-for-code-generation","title":"Test-Driven Development for Code Generation","date":"2024-02-21","arxiv_id":"2402.13521","repositories_listed":0,"syntology":null},{"url":null,"slug":"unit-testing-in-asp-revisited-language-and","title":"Unit Testing in ASP Revisited: Language and Test-Driven Development Environment","date":"2024-01-04","arxiv_id":"2401.02153","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm4tdd-best-practices-for-test-driven","title":"LLM4TDD: Best Practices for Test Driven Development Using Large Language Models","date":"2023-12-07","arxiv_id":"2312.04687","repositories_listed":0,"syntology":null},{"url":null,"slug":"testing-llms-on-code-generation-with-varying","title":"Testing LLMs on Code Generation with Varying Levels of Prompt Specificity","date":"2023-11-10","arxiv_id":"2311.07599","repositories_listed":0,"syntology":null},{"url":null,"slug":"timegym-debugging-for-time-series-modeling-in","title":"TimeGym: Debugging for Time Series Modeling in Python","date":"2021-05-04","arxiv_id":"2105.01404","repositories_listed":0,"syntology":null},{"url":null,"slug":"applied-awareness-test-driven-gui-development","title":"Applied Awareness: Test-Driven GUI Development using Computer Vision and Cryptography","date":"2020-06-05","arxiv_id":"2006.03725","repositories_listed":0,"syntology":null},{"url":null,"slug":"apertium-fin-eng-rule-based-shallow-machine","title":"Apertium-fin-eng--Rule-based Shallow Machine Translation for WMT 2019 Shared Task","date":"2019-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"more-effective-ontology-authoring-with-test","title":"More Effective Ontology Authoring with Test-Driven Development","date":"2018-12-14","arxiv_id":"1812.06015","repositories_listed":0,"syntology":null},{"url":null,"slug":"test-driven-development-of-ontologies","title":"Test-Driven Development of ontologies (extended version)","date":"2015-12-19","arxiv_id":"1512.06211","repositories_listed":0,"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"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":3,"papers_where_code_ran_first_page":"/task/test-driven-development/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/test-driven-development/papers/ran/1","json":"/task/test-driven-development/papers/ran/1.json","rows":3}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"bcfd6cd612bd7ef7b880ccc6e01b8f8364a5d48e7bec5a20c9e340e9a221ec30","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}