{"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/answer-selection/papers/ran/1","list_of":"/task/answer-selection","task":"Answer Selection","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":[1,7],"of":7,"counts":{"archive_papers_tagged":171,"with_a_code_link":52,"where_syntology_ran_a_sample":7,"not_listed_spam_title":0,"listed":171,"listed_where_code_ran":7,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":7,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":7,"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/answer-selection/papers/ran/1","prev":null,"next":null,"papers":[{"url":"/paper/ada-leval-evaluating-long-context-llms-with","slug":"ada-leval-evaluating-long-context-llms-with","title":"Ada-LEval: Evaluating long-context LLMs with length-adaptable benchmarks","date":"2024-04-09","arxiv_id":"2404.06480","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"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) · 0 unverified","sample_list":"/paper/ada-leval-evaluating-long-context-llms-with#ran","syntology_url":"https://syntology.ai/paper/2404.06480","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.06480"}},"official":{"repos":["open-compass/ada-leval"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/when-benchmarks-are-targets-revealing-the","slug":"when-benchmarks-are-targets-revealing-the","title":"When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards","date":"2024-02-01","arxiv_id":"2402.01781","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/when-benchmarks-are-targets-revealing-the#ran","syntology_url":"https://syntology.ai/paper/2402.01781","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01781"}},"official":{"repos":["national-center-for-ai-saudi-arabia/lm-evaluation-harness"],"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/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/simple-and-effective-text-matching-with-1","slug":"simple-and-effective-text-matching-with-1","title":"Simple and Effective Text Matching with Richer Alignment Features","date":"2019-08-01","arxiv_id":"1908.00300","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/simple-and-effective-text-matching-with-1#ran","syntology_url":"https://syntology.ai/paper/1908.00300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.00300"}},"official":{"repos":["hitvoice/RE2"],"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/gated-attention-readers-for-text","slug":"gated-attention-readers-for-text","title":"Gated-Attention Readers for Text Comprehension","date":"2016-06-05","arxiv_id":"1606.01549","repositories_listed":4,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/gated-attention-readers-for-text#ran","syntology_url":"https://syntology.ai/paper/1606.01549","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.01549"}},"official":{"repos":["bdhingra/ga-reader"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/neural-variational-inference-for-text","slug":"neural-variational-inference-for-text","title":"Neural Variational Inference for Text Processing","date":"2015-11-19","arxiv_id":"1511.06038","repositories_listed":6,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/neural-variational-inference-for-text#ran","syntology_url":"https://syntology.ai/paper/1511.06038","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.06038"}},"official":null}},{"url":"/paper/the-ubuntu-dialogue-corpus-a-large-dataset-1","slug":"the-ubuntu-dialogue-corpus-a-large-dataset-1","title":"The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems","date":"2015-06-30","arxiv_id":"1506.08909","repositories_listed":21,"syntology":{"n":26,"n_ran":15,"n_constructed":0,"n_ran_checked":14,"n_instrument":1,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":5,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/the-ubuntu-dialogue-corpus-a-large-dataset-1#ran","syntology_url":"https://syntology.ai/paper/1506.08909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1506.08909"}},"official":{"repos":["npow/ubottu"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}],"record_sha256":"5e245df3a9c4166bee803770fb106af7274a847555131870eff05bd25a572463","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}