{"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":"/dataset/apps/papers/ran/1","list_of":"/dataset/apps","dataset":"APPS","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","key_notes":{"samples_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'","samples_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)"},"order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"rows":[1,10],"of":10,"counts":{"papers_with_a_benchmark_row":11,"with_a_code_link":11,"where_syntology_ran_a_sample":10,"not_listed_spam_title":0,"listed":11,"listed_where_code_ran":10,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":8,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":8,"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 with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/dataset/apps/papers/ran/1","prev":null,"next":null,"papers":[{"paper":"/paper/codesim-multi-agent-code-generation-and-1","slug":"codesim-multi-agent-code-generation-and-1","title":"CODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debugging","date":"2025-02-08","arxiv_id":"2502.05664","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/codesim-multi-agent-code-generation-and-1#ran","syntology_url":"https://syntology.ai/paper/2502.05664","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.05664"}}}},{"paper":"/paper/planning-driven-programming-a-large-language","slug":"planning-driven-programming-a-large-language","title":"Planning-Driven Programming: A Large Language Model Programming Workflow","date":"2024-11-21","arxiv_id":"2411.14503","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":9,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["you68681/lpw"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/planning-driven-programming-a-large-language#ran","syntology_url":"https://syntology.ai/paper/2411.14503","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.14503"}}}},{"paper":"/paper/mapcoder-multi-agent-code-generation-for","slug":"mapcoder-multi-agent-code-generation-for","title":"MapCoder: Multi-Agent Code Generation for Competitive Problem Solving","date":"2024-05-18","arxiv_id":"2405.11403","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":10,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["md-ashraful-pramanik/mapcoder"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mapcoder-multi-agent-code-generation-for#ran","syntology_url":"https://syntology.ai/paper/2405.11403","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.11403"}}}},{"paper":"/paper/deepseek-coder-when-the-large-language-model","slug":"deepseek-coder-when-the-large-language-model","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","date":"2024-01-25","arxiv_id":"2401.14196","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":10,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["deepseek-ai/DeepSeek-Coder"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deepseek-coder-when-the-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2401.14196","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.14196"}}}},{"paper":"/paper/motcoder-elevating-large-language-models-with","slug":"motcoder-elevating-large-language-models-with","title":"MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks","date":"2023-12-26","arxiv_id":"2312.15960","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":8,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":8,"official":{"repos":["dvlab-research/motcoder"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/motcoder-elevating-large-language-models-with#ran","syntology_url":"https://syntology.ai/paper/2312.15960","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15960"}}}},{"paper":"/paper/codechain-towards-modular-code-generation","slug":"codechain-towards-modular-code-generation","title":"CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules","date":"2023-10-13","arxiv_id":"2310.08992","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["SalesforceAIResearch/CodeChain"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/codechain-towards-modular-code-generation#ran","syntology_url":"https://syntology.ai/paper/2310.08992","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.08992"}}}},{"paper":"/paper/codet-code-generation-with-generated-tests","slug":"codet-code-generation-with-generated-tests","title":"CodeT: Code Generation with Generated Tests","date":"2022-07-21","arxiv_id":"2207.10397","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["microsoft/codet"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/codet-code-generation-with-generated-tests#ran","syntology_url":"https://syntology.ai/paper/2207.10397","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.10397"}}}},{"paper":"/paper/coderl-mastering-code-generation-through","slug":"coderl-mastering-code-generation-through","title":"CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning","date":"2022-07-05","arxiv_id":"2207.01780","rows_on_this_dataset":4,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["salesforce/coderl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/coderl-mastering-code-generation-through#ran","syntology_url":"https://syntology.ai/paper/2207.01780","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.01780"}}}},{"paper":"/paper/evaluating-large-language-models-trained-on","slug":"evaluating-large-language-models-trained-on","title":"Evaluating Large Language Models Trained on Code","date":"2021-07-07","arxiv_id":"2107.03374","rows_on_this_dataset":1,"code_links":13,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":39,"samples_ran":26,"samples_constructed":0,"samples_ran_checked":24,"samples_ran_instrument_failed":2,"samples_unverified":13,"pointer_only_for_licence":4,"official":{"repos":["openai/human-eval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["found_in_text","listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/evaluating-large-language-models-trained-on#ran","syntology_url":"https://syntology.ai/paper/2107.03374","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.03374"}}}},{"paper":"/paper/measuring-coding-challenge-competence-with","slug":"measuring-coding-challenge-competence-with","title":"Measuring Coding Challenge Competence With APPS","date":"2021-05-20","arxiv_id":"2105.09938","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":11,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":2,"official":{"repos":["hendrycks/apps"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/measuring-coding-challenge-competence-with#ran","syntology_url":"https://syntology.ai/paper/2105.09938","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.09938"}}}}],"record_sha256":"8c2c4f575a0ae4f7ff5dd5e0fb9f9b372854c289ade2a4b8d6085111aaa8bfbf","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}