{"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/polynewsparallel","name":"PolyNewsParallel","full_name":null,"description_markdown":"PolyNews is a multilingual parallel dataset containing news titles 833 language pairs, spanning in 64 languages and 17 scripts.\r\n\r\nPolyNewsParallel aims to provide an easily-accessible, unified and de-duplicated dataset that combines three disparate data sources. It can be used for machine translation or text retrieval in both high-resource and low-resource languages.","description_withheld":null,"homepage":"https://huggingface.co/datasets/aiana94/polynews-parallel","introduced_date":"2024-06-18","introduced_date_note":null,"introduced_by":{"paper":"/paper/news-without-borders-domain-adaptation-of","title":"News Without Borders: Domain Adaptation of Multilingual Sentence Embeddings for Cross-lingual News Recommendation","first_author":"Andreea Iana","url":null},"license":{"name":"CC-BY-NC-4.0","url":"https://spdx.org/licenses/CC-BY-NC-4.0"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Machine Translation","url":"/task/machine-translation","datasets_with_task":"/datasets/task/machine-translation"},{"name":"Text Retrieval","url":"/task/text-retrieval","datasets_with_task":"/datasets/task/text-retrieval"},{"name":"News Retrieval","url":"/task/news-retrieval","datasets_with_task":"/datasets/task/news-retrieval"},{"name":"NMT","url":"/task/nmt","datasets_with_task":"/datasets/task/nmt"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"French","url":"/datasets/language/french"},{"name":"Spanish","url":"/datasets/language/spanish"},{"name":"German","url":"/datasets/language/german"},{"name":"Italian","url":"/datasets/language/italian"},{"name":"Chinese","url":"/datasets/language/chinese"},{"name":"Bengali","url":"/datasets/language/bengali"},{"name":"Japanese","url":"/datasets/language/japanese"},{"name":"Russian","url":"/datasets/language/russian"},{"name":"Portuguese","url":"/datasets/language/portuguese"},{"name":"Albanian","url":"/datasets/language/albanian"},{"name":"Amharic","url":"/datasets/language/amharic"},{"name":"Arabic","url":"/datasets/language/arabic"},{"name":"Bambara","url":"/datasets/language/bambara"},{"name":"Bulgarian","url":"/datasets/language/bulgarian"},{"name":"Catalan","url":"/datasets/language/catalan"},{"name":"Czech","url":"/datasets/language/czech"},{"name":"Danish","url":"/datasets/language/danish"},{"name":"Dutch","url":"/datasets/language/dutch"},{"name":"Estonian","url":"/datasets/language/estonian"},{"name":"Finnish","url":"/datasets/language/finnish"},{"name":"Hebrew","url":"/datasets/language/hebrew"},{"name":"Hindi","url":"/datasets/language/hindi"},{"name":"Hungarian","url":"/datasets/language/hungarian"},{"name":"Indonesian","url":"/datasets/language/indonesian"},{"name":"Kazakh","url":"/datasets/language/kazakh"},{"name":"Korean","url":"/datasets/language/korean"},{"name":"Latvian","url":"/datasets/language/latvian"},{"name":"Lithuanian","url":"/datasets/language/lithuanian"},{"name":"Nigerian Pidgin","url":"/datasets/language/nigerian-pidgin"},{"name":"Persian","url":"/datasets/language/persian"},{"name":"Polish","url":"/datasets/language/polish"},{"name":"Romanian","url":"/datasets/language/romanian"},{"name":"Serbian","url":"/datasets/language/serbian"},{"name":"Swedish","url":"/datasets/language/swedish"},{"name":"Thai","url":"/datasets/language/thai"},{"name":"Turkish","url":"/datasets/language/turkish"},{"name":"Urdu","url":"/datasets/language/urdu"},{"name":"Wolof","url":"/datasets/language/wolof"},{"name":"Yoruba","url":"/datasets/language/yoruba"},{"name":"Greek","url":"/datasets/language/greek"},{"name":"Swahili","url":"/datasets/language/swahili"},{"name":"Aymara","url":"/datasets/language/aymara"},{"name":"Ewe","url":"/datasets/language/ewe"},{"name":"Filipino","url":"/datasets/language/filipino"},{"name":"Fon","url":"/datasets/language/fon"},{"name":"Gujarati","url":"/datasets/language/gujarati"},{"name":"Hausa","url":"/datasets/language/hausa"},{"name":"Igbo","url":"/datasets/language/igbo"},{"name":"Central Khmer","url":"/datasets/language/central-khmer"},{"name":"Kurdish","url":"/datasets/language/kurdish"},{"name":"Ganda","url":"/datasets/language/ganda"},{"name":"Luo (Kenya and Tanzania)","url":"/datasets/language/luo-kenya-and-tanzania"},{"name":"Macedonian","url":"/datasets/language/macedonian"},{"name":"Malagasy","url":"/datasets/language/malagasy"},{"name":"Mossi","url":"/datasets/language/mossi"},{"name":"Burmese","url":"/datasets/language/burmese"},{"name":"Nepali (macrolanguage)","url":"/datasets/language/nepali-macrolanguage"},{"name":"Odia","url":"/datasets/language/odia"},{"name":"Western Panjabi","url":"/datasets/language/western-panjabi"},{"name":"Tetum","url":"/datasets/language/tetum"},{"name":"Tswana","url":"/datasets/language/tswana"},{"name":"Zulu","url":"/datasets/language/zulu"}],"variants":["PolyNewsParallel"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"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":0,"of":0,"counts":{"papers_with_a_benchmark_row":0,"with_a_code_link":0,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":0,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"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":[],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[],"papers_where_code_ran":0,"papers_where_code_ran_first_page":null,"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":[],"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":0,"samples_harvested":0,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":0,"papers_with_a_run_with_no_instrument_failure":0,"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":"4d4fce6c0476817b1262f471b3b86fee1a8617282d77d94d9a56e46adac33652","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}