{"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/bug-fixing/papers/ran/1","list_of":"/task/bug-fixing","task":"Bug fixing","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","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 task or check it against the task'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.","page":1,"pages_in_order":1,"rows_per_page":100,"rows":[1,8],"of":8,"counts":{"archive_papers_tagged":62,"with_a_code_link":31,"where_syntology_ran_a_sample":8,"not_listed_spam_title":0,"listed":62,"listed_where_code_ran":8,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":8,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":8,"listed_every_run_a_failure_of_syntologys_instrument":0,"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"},"first_page":"/task/bug-fixing/papers/ran/1","prev":null,"next":null,"papers":[{"url":"/paper/swe-dev-evaluating-and-training-autonomous","slug":"swe-dev-evaluating-and-training-autonomous","title":"SWE-Dev: Evaluating and Training Autonomous Feature-Driven Software Development","date":"2025-05-22","arxiv_id":"2505.16975","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/swe-dev-evaluating-and-training-autonomous#ran","syntology_url":"https://syntology.ai/paper/2505.16975","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.16975"}},"official":{"repos":["dorothyduuu/swe-dev"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cornstack-high-quality-contrastive-data-for","slug":"cornstack-high-quality-contrastive-data-for","title":"CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking","date":"2024-12-01","arxiv_id":"2412.01007","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/cornstack-high-quality-contrastive-data-for#ran","syntology_url":"https://syntology.ai/paper/2412.01007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.01007"}},"official":{"repos":["gangiswag/cornstack"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/metrex-a-benchmark-for-verilog-code-metric","slug":"metrex-a-benchmark-for-verilog-code-metric","title":"MetRex: A Benchmark for Verilog Code Metric Reasoning Using LLMs","date":"2024-11-05","arxiv_id":"2411.03471","repositories_listed":1,"syntology":{"n":13,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":13,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/metrex-a-benchmark-for-verilog-code-metric#ran","syntology_url":"https://syntology.ai/paper/2411.03471","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.03471"}},"official":{"repos":["scale-lab/MetRex"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/from-code-to-correctness-closing-the-last","slug":"from-code-to-correctness-closing-the-last","title":"From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging","date":"2024-10-02","arxiv_id":"2410.01215","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/from-code-to-correctness-closing-the-last#ran","syntology_url":"https://syntology.ai/paper/2410.01215","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01215"}},"official":{"repos":["YerbaPage/MGDebugger"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/autocoderover-autonomous-program-improvement","slug":"autocoderover-autonomous-program-improvement","title":"AutoCodeRover: Autonomous Program Improvement","date":"2024-04-08","arxiv_id":"2404.05427","repositories_listed":5,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/autocoderover-autonomous-program-improvement#ran","syntology_url":"https://syntology.ai/paper/2404.05427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05427"}},"official":{"repos":["nus-apr/auto-code-rover"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/swe-bench-can-language-models-resolve-real","slug":"swe-bench-can-language-models-resolve-real","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","date":"2023-10-10","arxiv_id":"2310.06770","repositories_listed":8,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/swe-bench-can-language-models-resolve-real#ran","syntology_url":"https://syntology.ai/paper/2310.06770","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06770"}},"official":null}},{"url":"/paper/gpt-4-technical-report-1","slug":"gpt-4-technical-report-1","title":"GPT-4 Technical Report","date":"2023-03-15","arxiv_id":"2303.08774","repositories_listed":11,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gpt-4-technical-report-1#ran","syntology_url":"https://syntology.ai/paper/2303.08774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08774"}},"official":{"repos":["openai/evals"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/fixeval-execution-based-evaluation-of-program","slug":"fixeval-execution-based-evaluation-of-program","title":"FixEval: Execution-based Evaluation of Program Fixes for Programming Problems","date":"2022-06-15","arxiv_id":"2206.07796","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/fixeval-execution-based-evaluation-of-program#ran","syntology_url":"https://syntology.ai/paper/2206.07796","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.07796"}},"official":{"repos":["mahimanzum/fixeval"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}}],"record_sha256":"758343b94dfa297eb9663c4c1af81c6d9841c77072f162219910ea088d329521","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}