{"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/multiple-choice-qa/papers/ran/1","list_of":"/task/multiple-choice-qa","task":"Multiple Choice Question Answering (MCQA)","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":[1,16],"of":16,"counts":{"archive_papers_tagged":65,"with_a_code_link":37,"where_syntology_ran_a_sample":16,"not_listed_spam_title":0,"listed":65,"listed_where_code_ran":16,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":14,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":14,"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"},"first_page":"/task/multiple-choice-qa/papers/ran/1","prev":null,"next":null,"papers":[{"url":"/paper/answer-assemble-ace-understanding-how","slug":"answer-assemble-ace-understanding-how","title":"Answer, Assemble, Ace: Understanding How Transformers Answer Multiple Choice Questions","date":"2024-07-21","arxiv_id":"2407.15018","repositories_listed":0,"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":0,"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/answer-assemble-ace-understanding-how#ran","syntology_url":"https://syntology.ai/paper/2407.15018","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.15018"}},"official":null}},{"url":"/paper/econlogicqa-a-question-answering-benchmark","slug":"econlogicqa-a-question-answering-benchmark","title":"EconLogicQA: A Question-Answering Benchmark for Evaluating Large Language Models in Economic Sequential Reasoning","date":"2024-05-13","arxiv_id":"2405.07938","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"7 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; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/econlogicqa-a-question-answering-benchmark#ran","syntology_url":"https://syntology.ai/paper/2405.07938","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.07938"}},"official":{"repos":["yinzhu-quan/lm-evaluation-harness"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/adamole-fine-tuning-large-language-models","slug":"adamole-fine-tuning-large-language-models","title":"AdaMoLE: Fine-Tuning Large Language Models with Adaptive Mixture of Low-Rank Adaptation Experts","date":"2024-05-01","arxiv_id":"2405.00361","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/adamole-fine-tuning-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2405.00361","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.00361"}},"official":{"repos":["zefang-liu/adamole"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/artifacts-or-abduction-how-do-llms-answer","slug":"artifacts-or-abduction-how-do-llms-answer","title":"Artifacts or Abduction: How Do LLMs Answer Multiple-Choice Questions Without the Question?","date":"2024-02-19","arxiv_id":"2402.12483","repositories_listed":1,"syntology":{"n":10,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":10,"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) · 6 unverified","sample_list":"/paper/artifacts-or-abduction-how-do-llms-answer#ran","syntology_url":"https://syntology.ai/paper/2402.12483","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12483"}},"official":{"repos":["nbalepur/mcqa-artifacts"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/meditron-70b-scaling-medical-pretraining-for","slug":"meditron-70b-scaling-medical-pretraining-for","title":"MEDITRON-70B: Scaling Medical Pretraining for Large Language Models","date":"2023-11-27","arxiv_id":"2311.16079","repositories_listed":1,"syntology":{"n":14,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/meditron-70b-scaling-medical-pretraining-for#ran","syntology_url":"https://syntology.ai/paper/2311.16079","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.16079"}},"official":{"repos":["epfllm/meditron"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/fool-your-vision-and-language-model-with","slug":"fool-your-vision-and-language-model-with","title":"Fool Your (Vision and) Language Model With Embarrassingly Simple Permutations","date":"2023-10-02","arxiv_id":"2310.01651","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/fool-your-vision-and-language-model-with#ran","syntology_url":"https://syntology.ai/paper/2310.01651","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01651"}},"official":{"repos":["ys-zong/foolyourvllms"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/llama-2-open-foundation-and-fine-tuned-chat","slug":"llama-2-open-foundation-and-fine-tuned-chat","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","date":"2023-07-18","arxiv_id":"2307.09288","repositories_listed":19,"syntology":{"n":52,"n_ran":33,"n_constructed":7,"n_ran_checked":22,"n_instrument":11,"n_unverified":19,"n_honours":1,"n_violates":1,"n_no_contract":20,"n_pointer_only":20,"phrase":"33 ran (of which 7 constructed an object rather than computing a result; 22 with no instrument failure: 1 honoured, 1 violated, 20 with no contract checked; 11 where Syntology's instrument failed) · 19 unverified","sample_list":"/paper/llama-2-open-foundation-and-fine-tuned-chat#ran","syntology_url":"https://syntology.ai/paper/2307.09288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09288"}},"official":{"repos":["facebookresearch/llama"],"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/galactica-a-large-language-model-for-science-1","slug":"galactica-a-large-language-model-for-science-1","title":"Galactica: A Large Language Model for Science","date":"2022-11-16","arxiv_id":"2211.09085","repositories_listed":1,"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":0,"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/galactica-a-large-language-model-for-science-1#ran","syntology_url":"https://syntology.ai/paper/2211.09085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09085"}},"official":{"repos":["paperswithcode/galai"],"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/leveraging-large-language-models-for-multiple","slug":"leveraging-large-language-models-for-multiple","title":"Leveraging Large Language Models for Multiple Choice Question Answering","date":"2022-10-22","arxiv_id":"2210.12353","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":3,"n_ran_checked":3,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/leveraging-large-language-models-for-multiple#ran","syntology_url":"https://syntology.ai/paper/2210.12353","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.12353"}},"official":{"repos":["byu-pccl/leveraging-llms-for-mcqa"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/variational-open-domain-question-answering","slug":"variational-open-domain-question-answering","title":"Variational Open-Domain Question Answering","date":"2022-09-23","arxiv_id":"2210.06345","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/variational-open-domain-question-answering#ran","syntology_url":"https://syntology.ai/paper/2210.06345","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06345"}},"official":{"repos":["findzebra/fz-openqa","VodLM/vod"],"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":["official"]}}},{"url":"/paper/can-large-language-models-reason-about","slug":"can-large-language-models-reason-about","title":"Can large language models reason about medical questions?","date":"2022-07-17","arxiv_id":"2207.08143","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/can-large-language-models-reason-about#ran","syntology_url":"https://syntology.ai/paper/2207.08143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.08143"}},"official":{"repos":["vlievin/medical-reasoning"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/clues-before-answers-generation-enhanced","slug":"clues-before-answers-generation-enhanced","title":"Clues Before Answers: Generation-Enhanced Multiple-Choice QA","date":"2022-04-30","arxiv_id":"2205.00274","repositories_listed":1,"syntology":{"n":11,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/clues-before-answers-generation-enhanced#ran","syntology_url":"https://syntology.ai/paper/2205.00274","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.00274"}},"official":{"repos":["nju-websoft/genmc"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/palm-scaling-language-modeling-with-pathways-1","slug":"palm-scaling-language-modeling-with-pathways-1","title":"PaLM: Scaling Language Modeling with Pathways","date":"2022-04-05","arxiv_id":"2204.02311","repositories_listed":7,"syntology":{"n":37,"n_ran":32,"n_constructed":16,"n_ran_checked":24,"n_instrument":8,"n_unverified":5,"n_honours":2,"n_violates":1,"n_no_contract":21,"n_pointer_only":0,"phrase":"32 ran (of which 16 constructed an object rather than computing a result; 24 with no instrument failure: 2 honoured, 1 violated, 21 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/palm-scaling-language-modeling-with-pathways-1#ran","syntology_url":"https://syntology.ai/paper/2204.02311","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02311"}},"official":null}},{"url":"/paper/training-compute-optimal-large-language","slug":"training-compute-optimal-large-language","title":"Training Compute-Optimal Large Language Models","date":"2022-03-29","arxiv_id":"2203.15556","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":3,"n_ran_checked":5,"n_instrument":3,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"8 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/training-compute-optimal-large-language#ran","syntology_url":"https://syntology.ai/paper/2203.15556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15556"}},"official":null}},{"url":"/paper/does-transliteration-help-multilingual","slug":"does-transliteration-help-multilingual","title":"Does Transliteration Help Multilingual Language Modeling?","date":"2022-01-29","arxiv_id":"2201.12501","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":0,"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/does-transliteration-help-multilingual#ran","syntology_url":"https://syntology.ai/paper/2201.12501","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.12501"}},"official":{"repos":["ibraheem-moosa/xlm-indic"],"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/from-recognition-to-cognition-visual","slug":"from-recognition-to-cognition-visual","title":"From Recognition to Cognition: Visual Commonsense Reasoning","date":"2018-11-27","arxiv_id":"1811.10830","repositories_listed":4,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/from-recognition-to-cognition-visual#ran","syntology_url":"https://syntology.ai/paper/1811.10830","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.10830"}},"official":null}}],"record_sha256":"ad34ded5dd657b74ff07e03341af655b710b45945922a1ee633e883c425deb00","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}