{"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/language-model-evaluation/papers/ran/1","list_of":"/task/language-model-evaluation","task":"Language Model Evaluation","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":[1,12],"of":12,"counts":{"archive_papers_tagged":69,"with_a_code_link":31,"where_syntology_ran_a_sample":12,"not_listed_spam_title":0,"listed":69,"listed_where_code_ran":12,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":11,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":11,"listed_every_run_a_failure_of_syntologys_instrument":1,"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/language-model-evaluation/papers/ran/1","prev":null,"next":null,"papers":[{"url":"/paper/dart-eval-a-comprehensive-dna-language-model","slug":"dart-eval-a-comprehensive-dna-language-model","title":"DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA","date":"2024-12-06","arxiv_id":"2412.05430","repositories_listed":1,"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":16,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/dart-eval-a-comprehensive-dna-language-model#ran","syntology_url":"https://syntology.ai/paper/2412.05430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.05430"}},"official":{"repos":["kundajelab/dart-eval"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/mitigating-the-bias-of-large-language-model","slug":"mitigating-the-bias-of-large-language-model","title":"Mitigating the Bias of Large Language Model Evaluation","date":"2024-09-25","arxiv_id":"2409.16788","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mitigating-the-bias-of-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2409.16788","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.16788"}},"official":{"repos":["Joe-Hall-Lee/Debias"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-suite-for-acoustic-language-model","slug":"a-suite-for-acoustic-language-model","title":"Salmon: A Suite for Acoustic Language Model Evaluation","date":"2024-09-11","arxiv_id":"2409.07437","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-suite-for-acoustic-language-model#ran","syntology_url":"https://syntology.ai/paper/2409.07437","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.07437"}},"official":{"repos":["slp-rl/salmon"],"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"]}}},{"url":"/paper/on-speeding-up-language-model-evaluation","slug":"on-speeding-up-language-model-evaluation","title":"On Speeding Up Language Model Evaluation","date":"2024-07-08","arxiv_id":"2407.06172","repositories_listed":0,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/on-speeding-up-language-model-evaluation#ran","syntology_url":"https://syntology.ai/paper/2407.06172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.06172"}},"official":null}},{"url":"/paper/paraphrase-and-solve-exploring-and-exploiting","slug":"paraphrase-and-solve-exploring-and-exploiting","title":"Paraphrase and Solve: Exploring and Exploiting the Impact of Surface Form on Mathematical Reasoning in Large Language Models","date":"2024-04-17","arxiv_id":"2404.11500","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/paraphrase-and-solve-exploring-and-exploiting#ran","syntology_url":"https://syntology.ai/paper/2404.11500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.11500"}},"official":{"repos":["yue-llm-pit/scop"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/arabicmmlu-assessing-massive-multitask","slug":"arabicmmlu-assessing-massive-multitask","title":"ArabicMMLU: Assessing Massive Multitask Language Understanding in Arabic","date":"2024-02-20","arxiv_id":"2402.12840","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/arabicmmlu-assessing-massive-multitask#ran","syntology_url":"https://syntology.ai/paper/2402.12840","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12840"}},"official":{"repos":["mbzuai-nlp/arabicmmlu"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/avoiding-data-contamination-in-language-model","slug":"avoiding-data-contamination-in-language-model","title":"LatestEval: Addressing Data Contamination in Language Model Evaluation through Dynamic and Time-Sensitive Test Construction","date":"2023-12-19","arxiv_id":"2312.12343","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/avoiding-data-contamination-in-language-model#ran","syntology_url":"https://syntology.ai/paper/2312.12343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12343"}},"official":{"repos":["liyucheng09/latesteval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/medeval-a-multi-level-multi-task-and-multi","slug":"medeval-a-multi-level-multi-task-and-multi","title":"MedEval: A Multi-Level, Multi-Task, and Multi-Domain Medical Benchmark for Language Model Evaluation","date":"2023-10-21","arxiv_id":"2310.14088","repositories_listed":0,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"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) · 3 unverified","sample_list":"/paper/medeval-a-multi-level-multi-task-and-multi#ran","syntology_url":"https://syntology.ai/paper/2310.14088","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.14088"}},"official":null}},{"url":"/paper/scieval-a-multi-level-large-language-model","slug":"scieval-a-multi-level-large-language-model","title":"SciEval: A Multi-Level Large Language Model Evaluation Benchmark for Scientific Research","date":"2023-08-25","arxiv_id":"2308.13149","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scieval-a-multi-level-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2308.13149","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.13149"}},"official":{"repos":["opendfm/bai-scieval","opendfm/scieval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/flask-fine-grained-language-model-evaluation","slug":"flask-fine-grained-language-model-evaluation","title":"FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets","date":"2023-07-20","arxiv_id":"2307.10928","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/flask-fine-grained-language-model-evaluation#ran","syntology_url":"https://syntology.ai/paper/2307.10928","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.10928"}},"official":{"repos":["kaistai/flask"],"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/csts-conditional-semantic-textual-similarity","slug":"csts-conditional-semantic-textual-similarity","title":"C-STS: Conditional Semantic Textual Similarity","date":"2023-05-24","arxiv_id":"2305.15093","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/csts-conditional-semantic-textual-similarity#ran","syntology_url":"https://syntology.ai/paper/2305.15093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15093"}},"official":{"repos":["princeton-nlp/c-sts"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/bigbio-a-framework-for-data-centric","slug":"bigbio-a-framework-for-data-centric","title":"BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing","date":"2022-06-30","arxiv_id":"2206.15076","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bigbio-a-framework-for-data-centric#ran","syntology_url":"https://syntology.ai/paper/2206.15076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.15076"}},"official":{"repos":["bigscience-workshop/biomedical"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}}],"record_sha256":"b43f0f0b338a4e958ef53f58c878c790c5fdca8491eec17e571efe49abbd2705","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}