{"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/narrativeqa","name":"NarrativeQA","full_name":"NarrativeQA","description_markdown":"The NarrativeQA dataset includes a list of documents with Wikipedia summaries, links to full stories, and questions and answers.\r\n\r\nSource: [DeepMind](https://deepmind.com/research/open-source/narrativeqa)\r\nImage Source: [Kočiský et al ](https://arxiv.org/pdf/1712.07040v1.pdf)","description_withheld":null,"homepage":"https://deepmind.com/research/open-source/narrativeqa","introduced_date":"2017-12-19","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-narrativeqa-reading-comprehension","title":"The NarrativeQA Reading Comprehension Challenge","first_author":"Tomáš Kočiský","url":null},"license":{"name":"Apache-2.0 License","url":"https://github.com/deepmind/narrativeqa"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Reading Comprehension","url":"/task/reading-comprehension","datasets_with_task":"/datasets/task/reading-comprehension"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["NarrativeQA"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/narrativeqa","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/narrativeqa_manual","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/deepmind/narrativeqa_manual","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/deepmind/narrativeqa","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/facebookresearch/ParlAI","url":"https://parl.ai/docs/tasks.html#narrativeqa","frameworks":["pytorch"]}],"num_papers_in_archive":206,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/question-answering-on-narrativeqa","task":"Question Answering","dataset_variant":"NarrativeQA","rows":10,"metrics":["Rouge-L","BLEU-1","BLEU-4","METEOR"],"first_row_in_archive_order":{"model":"Masque (NarrativeQA + MS MARCO)","paper":"/paper/multi-style-generative-reading-comprehension","metrics":{"BLEU-1":"54.11","BLEU-4":"30.43","METEOR":"26.13","Rouge-L":"59.87"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","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,"shown":9,"of":9,"counts":{"papers_with_a_benchmark_row":9,"with_a_code_link":6,"where_syntology_ran_a_sample":4,"not_listed_spam_title":0,"listed":9,"listed_where_code_ran":4,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":3,"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 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"},"items":[{"paper":"/paper/distilling-knowledge-from-reader-to-retriever-1","slug":"distilling-knowledge-from-reader-to-retriever-1","title":"Distilling Knowledge from Reader to Retriever for Question Answering","date":"2020-12-08","arxiv_id":"2012.04584","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+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":1,"official":{"repos":["facebookresearch/FiD"],"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/distilling-knowledge-from-reader-to-retriever-1#ran","syntology_url":"https://syntology.ai/paper/2012.04584","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.04584"}}}},{"paper":"/paper/a-discrete-hard-em-approach-for-weakly","slug":"a-discrete-hard-em-approach-for-weakly","title":"A Discrete Hard EM Approach for Weakly Supervised Question Answering","date":"2019-09-11","arxiv_id":"1909.04849","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["shmsw25/qa-hard-em"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-discrete-hard-em-approach-for-weakly#ran","syntology_url":"https://syntology.ai/paper/1909.04849","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.04849"}}}},{"paper":"/paper/multi-style-generative-reading-comprehension","slug":"multi-style-generative-reading-comprehension","title":"Multi-style Generative Reading Comprehension","date":"2019-01-08","arxiv_id":"1901.02262","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/densely-connected-attention-propagation-for","slug":"densely-connected-attention-propagation-for","title":"Densely Connected Attention Propagation for Reading Comprehension","date":"2018-11-10","arxiv_id":"1811.04210","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/cut-to-the-chase-a-context-zoom-in-network","slug":"cut-to-the-chase-a-context-zoom-in-network","title":"Cut to the Chase: A Context Zoom-in Network for Reading Comprehension","date":"2018-10-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multi-granular-sequence-encoding-via-dilated","slug":"multi-granular-sequence-encoding-via-dilated","title":"Multi-Granular Sequence Encoding via Dilated Compositional Units for Reading Comprehension","date":"2018-10-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/commonsense-for-generative-multi-hop-question","slug":"commonsense-for-generative-multi-hop-question","title":"Commonsense for Generative Multi-Hop Question Answering Tasks","date":"2018-09-17","arxiv_id":"1809.06309","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["yicheng-w/CommonSenseMultiHopQA"],"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":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/commonsense-for-generative-multi-hop-question#ran","syntology_url":"https://syntology.ai/paper/1809.06309","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.06309"}}}},{"paper":"/paper/the-narrativeqa-reading-comprehension","slug":"the-narrativeqa-reading-comprehension","title":"The NarrativeQA Reading Comprehension Challenge","date":"2017-12-19","arxiv_id":"1712.07040","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/bidirectional-attention-flow-for-machine","slug":"bidirectional-attention-flow-for-machine","title":"Bidirectional Attention Flow for Machine Comprehension","date":"2016-11-05","arxiv_id":"1611.01603","rows_on_this_dataset":1,"code_links":27,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":5,"samples_unverified":2,"pointer_only_for_licence":7,"official":{"repos":["allenai/bi-att-flow"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bidirectional-attention-flow-for-machine#ran","syntology_url":"https://syntology.ai/paper/1611.01603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.01603"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/distilling-knowledge-from-reader-to-retriever-1","slug":"distilling-knowledge-from-reader-to-retriever-1","title":"Distilling Knowledge from Reader to Retriever for Question Answering","date":"2020-12-08","arxiv_id":"2012.04584","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+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":1,"official":{"repos":["facebookresearch/FiD"],"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/distilling-knowledge-from-reader-to-retriever-1#ran","syntology_url":"https://syntology.ai/paper/2012.04584","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.04584"}}}},{"paper":"/paper/a-discrete-hard-em-approach-for-weakly","slug":"a-discrete-hard-em-approach-for-weakly","title":"A Discrete Hard EM Approach for Weakly Supervised Question Answering","date":"2019-09-11","arxiv_id":"1909.04849","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["shmsw25/qa-hard-em"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-discrete-hard-em-approach-for-weakly#ran","syntology_url":"https://syntology.ai/paper/1909.04849","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.04849"}}}},{"paper":"/paper/multi-style-generative-reading-comprehension","slug":"multi-style-generative-reading-comprehension","title":"Multi-style Generative Reading Comprehension","date":"2019-01-08","arxiv_id":"1901.02262","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/densely-connected-attention-propagation-for","slug":"densely-connected-attention-propagation-for","title":"Densely Connected Attention Propagation for Reading Comprehension","date":"2018-11-10","arxiv_id":"1811.04210","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/cut-to-the-chase-a-context-zoom-in-network","slug":"cut-to-the-chase-a-context-zoom-in-network","title":"Cut to the Chase: A Context Zoom-in Network for Reading Comprehension","date":"2018-10-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multi-granular-sequence-encoding-via-dilated","slug":"multi-granular-sequence-encoding-via-dilated","title":"Multi-Granular Sequence Encoding via Dilated Compositional Units for Reading Comprehension","date":"2018-10-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/commonsense-for-generative-multi-hop-question","slug":"commonsense-for-generative-multi-hop-question","title":"Commonsense for Generative Multi-Hop Question Answering Tasks","date":"2018-09-17","arxiv_id":"1809.06309","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["yicheng-w/CommonSenseMultiHopQA"],"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":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/commonsense-for-generative-multi-hop-question#ran","syntology_url":"https://syntology.ai/paper/1809.06309","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.06309"}}}},{"paper":"/paper/the-narrativeqa-reading-comprehension","slug":"the-narrativeqa-reading-comprehension","title":"The NarrativeQA Reading Comprehension Challenge","date":"2017-12-19","arxiv_id":"1712.07040","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/bidirectional-attention-flow-for-machine","slug":"bidirectional-attention-flow-for-machine","title":"Bidirectional Attention Flow for Machine Comprehension","date":"2016-11-05","arxiv_id":"1611.01603","rows_on_this_dataset":1,"code_links":27,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":5,"samples_unverified":2,"pointer_only_for_licence":7,"official":{"repos":["allenai/bi-att-flow"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bidirectional-attention-flow-for-machine#ran","syntology_url":"https://syntology.ai/paper/1611.01603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.01603"}}}}],"papers_where_code_ran":4,"papers_where_code_ran_first_page":"/dataset/narrativeqa/papers/ran/1","papers_where_code_ran_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.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/narrativeqa/papers/ran/1","json":"/dataset/narrativeqa/papers/ran/1.json","rows":4}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":4,"samples_harvested":20,"samples_ran":16,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":6,"samples_unverified":4,"pointer_only_for_licence":9,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":4,"papers_with_a_run_with_no_instrument_failure":3,"papers_where_every_run_was_an_instrument_failure":1,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"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)"},"since_archive_judged":{"papers":2,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/question-answering-on-narrativeqa","since_archive":"/sota/question-answering-on-narrativeqa#since-judged","papers_judged":2,"placed":0}]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"09f44b3ef57a7fc0f6bfbb1281ba899a426d66e96e0ff491f671c75d97f7061d","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}