{"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/xquad","name":"XQuAD","full_name":"XQuAD","description_markdown":"XQuAD (Cross-lingual Question Answering Dataset) is a benchmark dataset for evaluating cross-lingual question answering performance. The dataset consists of a subset of 240 paragraphs and 1190 question-answer pairs from the development set of SQuAD v1.1 (Rajpurkar et al., 2016) together with their professional translations into ten languages: Spanish, German, Greek, Russian, Turkish, Arabic, Vietnamese, Thai, Chinese, and Hindi. Consequently, the dataset is entirely parallel across 11 languages.\r\n\r\nSource: [XQuAD](https://github.com/deepmind/xquad)\r\nImage Source: [https://arxiv.org/pdf/1910.11856v3.pdf](https://arxiv.org/pdf/1910.11856v3.pdf)","description_withheld":null,"homepage":"https://github.com/deepmind/xquad","introduced_date":"2019-10-25","introduced_date_note":null,"introduced_by":{"paper":"/paper/on-the-cross-lingual-transferability-of","title":"On the Cross-lingual Transferability of Monolingual Representations","first_author":"Mikel Artetxe","url":null},"license":{"name":"CC BY-SA 4.0","url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Reading Comprehension","url":"/task/reading-comprehension","datasets_with_task":"/datasets/task/reading-comprehension"},{"name":"Cross-Lingual Question Answering","url":"/task/cross-lingual-question-answering","datasets_with_task":"/datasets/task/cross-lingual-question-answering"}],"languages":[{"name":"Spanish","url":"/datasets/language/spanish"},{"name":"German","url":"/datasets/language/german"},{"name":"Chinese","url":"/datasets/language/chinese"},{"name":"Multilingual","url":"/datasets/language/multilingual"},{"name":"Russian","url":"/datasets/language/russian"},{"name":"Arabic","url":"/datasets/language/arabic"},{"name":"Hindi","url":"/datasets/language/hindi"},{"name":"Thai","url":"/datasets/language/thai"},{"name":"Turkish","url":"/datasets/language/turkish"},{"name":"Vietnamese","url":"/datasets/language/vietnamese"},{"name":"Greek","url":"/datasets/language/greek"}],"variants":["XQuAD","XQuAD (de)"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/xquad","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/juletxara/xquad_xtreme","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/google/xquad","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/xquad","frameworks":["tf","jax"]},{"repo":"https://github.com/deepmind/xquad","url":"https://github.com/deepmind/xquad","frameworks":[]}],"num_papers_in_archive":190,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/cross-lingual-question-answering-on-xquad","task":"Cross-Lingual Question Answering","dataset_variant":"XQuAD","rows":4,"metrics":["EM","F1","Average F1"],"first_row_in_archive_order":{"model":"ByT5 XXL","paper":"/paper/byt5-towards-a-token-free-future-with-pre","metrics":{"EM":"63.6","F1":"79.7"},"code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers/tree/master/src/transformers/models/byt5"},{"title":"google-research/byt5","url":"https://github.com/google-research/byt5"},{"title":"ufal/multilexnorm2021","url":"https://github.com/ufal/multilexnorm2021"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/byt5"},{"title":"yoreG123/Paddle-ByT5","url":"https://github.com/yoreG123/Paddle-ByT5"}]},"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":3,"of":3,"counts":{"papers_with_a_benchmark_row":3,"with_a_code_link":3,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":3,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":1,"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 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/mluke-the-power-of-entity-representations-in","slug":"mluke-the-power-of-entity-representations-in","title":"mLUKE: The Power of Entity Representations in Multilingual Pretrained Language Models","date":"2021-10-15","arxiv_id":"2110.08151","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/byt5-towards-a-token-free-future-with-pre","slug":"byt5-towards-a-token-free-future-with-pre","title":"ByT5: Towards a token-free future with pre-trained byte-to-byte models","date":"2021-05-28","arxiv_id":"2105.13626","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["google-research/byt5"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/byt5-towards-a-token-free-future-with-pre#ran","syntology_url":"https://syntology.ai/paper/2105.13626","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.13626"}}}},{"paper":"/paper/rethinking-embedding-coupling-in-pre-trained-1","slug":"rethinking-embedding-coupling-in-pre-trained-1","title":"Rethinking embedding coupling in pre-trained language models","date":"2020-10-24","arxiv_id":"2010.12821","rows_on_this_dataset":2,"code_links":4,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/mluke-the-power-of-entity-representations-in","slug":"mluke-the-power-of-entity-representations-in","title":"mLUKE: The Power of Entity Representations in Multilingual Pretrained Language Models","date":"2021-10-15","arxiv_id":"2110.08151","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/byt5-towards-a-token-free-future-with-pre","slug":"byt5-towards-a-token-free-future-with-pre","title":"ByT5: Towards a token-free future with pre-trained byte-to-byte models","date":"2021-05-28","arxiv_id":"2105.13626","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["google-research/byt5"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/byt5-towards-a-token-free-future-with-pre#ran","syntology_url":"https://syntology.ai/paper/2105.13626","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.13626"}}}},{"paper":"/paper/rethinking-embedding-coupling-in-pre-trained-1","slug":"rethinking-embedding-coupling-in-pre-trained-1","title":"Rethinking embedding coupling in pre-trained language models","date":"2020-10-24","arxiv_id":"2010.12821","rows_on_this_dataset":2,"code_links":4,"syntology":null}],"papers_where_code_ran":1,"papers_where_code_ran_first_page":"/dataset/xquad/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/xquad/papers/ran/1","json":"/dataset/xquad/papers/ran/1.json","rows":1}],"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":1,"samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":1,"papers_with_a_run_with_no_instrument_failure":1,"papers_where_every_run_was_an_instrument_failure":0,"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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"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":"c517b27f9c0290ba92777083b5479a676c40e1478fb43abcccaa670b577a4676","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}