{"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/multi-news","name":"Multi-News","full_name":"Multi-News","description_markdown":"**Multi-News**, consists of news articles and human-written summaries of these articles from the site newser.com. Each summary is professionally written by editors and includes links to the original articles cited.\r\n\r\nSource: [Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model](https://arxiv.org/pdf/1906.01749.pdf)\r\nImage Source: [https://arxiv.org/pdf/1906.01749.pdf](https://arxiv.org/pdf/1906.01749.pdf)","description_withheld":null,"homepage":"https://github.com/Alex-Fabbri/Multi-News","introduced_date":"2019-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/multi-news-a-large-scale-multi-document","title":"Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model","first_author":"Alexander R. Fabbri","url":null},"license":{"name":"Custom","url":"https://github.com/Alex-Fabbri/Multi-News"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Summarization","url":"/task/text-summarization","datasets_with_task":"/datasets/task/text-summarization"},{"name":"Document Summarization","url":"/task/document-summarization","datasets_with_task":"/datasets/task/document-summarization"},{"name":"Summarization","url":"/task/summarization","datasets_with_task":"/datasets/task/summarization"},{"name":"Multi-Document Summarization","url":"/task/multi-document-summarization","datasets_with_task":"/datasets/task/multi-document-summarization"},{"name":"Cross-Document Language Modeling","url":"/task/cross-document-language-modeling","datasets_with_task":"/datasets/task/cross-document-language-modeling"},{"name":"Information Threading","url":"/task/information-threading","datasets_with_task":"/datasets/task/information-threading"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["MultiNews val","MultiNews test","Multi-News","multi_news"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/alexfabbri/multi_news","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/multi_news","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/allenai/multinews_dense_mean","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/allenai/multinews_dense_oracle","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/allenai/multi_news_sparse","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/allenai/multinews_sparse_oracle","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/allenai/multinews_sparse_max","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/allenai/multinews_sparse_mean","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/allenai/multinews_dense_max","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/multi_news","frameworks":["tf","jax"]},{"repo":"https://github.com/Alex-Fabbri/Multi-News","url":"https://github.com/Alex-Fabbri/Multi-News","frameworks":["pytorch"]}],"num_papers_in_archive":122,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/multi-document-summarization-on-multi-news","task":"Multi-Document Summarization","dataset_variant":"Multi-News","rows":6,"metrics":["ROUGE-1","ROUGE-2","ROUGE-SU4","ROUGE-L"],"first_row_in_archive_order":{"model":"PRIMER","paper":"/paper/primer-pyramid-based-masked-sentence-pre","metrics":{"ROUGE-1":"49.9","ROUGE-2":"21.1","ROUGE-L":"25.9"},"code_links":[{"title":"allenai/primer","url":"https://github.com/allenai/primer"},{"title":"allenai/open-mds","url":"https://github.com/allenai/open-mds"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/longformer"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/cross-document-language-modeling-on-multinews","task":"Cross-Document Language Modeling","dataset_variant":"MultiNews val","rows":3,"metrics":["Perplexity"],"first_row_in_archive_order":{"model":"CD-LM","paper":"/paper/cross-document-language-modeling","metrics":{"Perplexity":"1.69"},"code_links":[{"title":"aviclu/cdlm","url":"https://github.com/aviclu/cdlm"},{"title":"aviclu/CD-LM","url":"https://github.com/aviclu/CD-LM"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/cross-document-language-modeling-on-multinews-1","task":"Cross-Document Language Modeling","dataset_variant":"MultiNews test","rows":3,"metrics":["Perplexity"],"first_row_in_archive_order":{"model":"CD-LM","paper":"/paper/cross-document-language-modeling","metrics":{"Perplexity":"1.76"},"code_links":[{"title":"aviclu/cdlm","url":"https://github.com/aviclu/cdlm"},{"title":"aviclu/CD-LM","url":"https://github.com/aviclu/CD-LM"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/information-threading-on-multi-news","task":"Information Threading","dataset_variant":"Multi-News","rows":1,"metrics":["NMI"],"first_row_in_archive_order":{"model":"SeqINT","paper":"/paper/identifying-chronological-and-coherent","metrics":{"NMI":"0.8008"},"code_links":[{"title":"hitt08/HINT","url":"https://github.com/hitt08/HINT"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/summarization-on-multi-news","task":"Summarization","dataset_variant":"multi_news","rows":0,"metrics":["ROUGE-1","ROUGE-2","ROUGE-L","ROUGE-LSUM","gen_len","loss"],"first_row_in_archive_order":null,"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":7,"of":7,"counts":{"papers_with_a_benchmark_row":7,"with_a_code_link":6,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":7,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":1,"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 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/identifying-chronological-and-coherent","slug":"identifying-chronological-and-coherent","title":"Identifying chronological and coherent information threads using 5W1H questions and temporal relationships","date":"2023-01-18","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/longt5-efficient-text-to-text-transformer-for","slug":"longt5-efficient-text-to-text-transformer-for","title":"LongT5: Efficient Text-To-Text Transformer for Long Sequences","date":"2021-12-15","arxiv_id":"2112.07916","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":["google-research/longt5"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/longt5-efficient-text-to-text-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2112.07916","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.07916"}}}},{"paper":"/paper/primer-pyramid-based-masked-sentence-pre","slug":"primer-pyramid-based-masked-sentence-pre","title":"PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization","date":"2021-10-16","arxiv_id":"2110.08499","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["allenai/primer"],"state":"official (archive's flag): 4 ran","n_ran":4,"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/primer-pyramid-based-masked-sentence-pre#ran","syntology_url":"https://syntology.ai/paper/2110.08499","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.08499"}}}},{"paper":"/paper/multi-document-summarization","slug":"multi-document-summarization","title":"Multi-Document Summarization withDeterminantal Point Process Attention","date":"2021-07-13","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/cross-document-language-modeling","slug":"cross-document-language-modeling","title":"CDLM: Cross-Document Language Modeling","date":"2021-01-02","arxiv_id":"2101.00406","rows_on_this_dataset":6,"code_links":2,"syntology":null},{"paper":"/paper/multi-news-a-large-scale-multi-document","slug":"multi-news-a-large-scale-multi-document","title":"Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model","date":"2019-06-04","arxiv_id":"1906.01749","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/bottom-up-abstractive-summarization","slug":"bottom-up-abstractive-summarization","title":"Bottom-Up Abstractive Summarization","date":"2018-08-31","arxiv_id":"1808.10792","rows_on_this_dataset":2,"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":0,"samples_ran_instrument_failed":5,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["sebastianGehrmann/bottom-up-summary"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bottom-up-abstractive-summarization#ran","syntology_url":"https://syntology.ai/paper/1808.10792","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.10792"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/identifying-chronological-and-coherent","slug":"identifying-chronological-and-coherent","title":"Identifying chronological and coherent information threads using 5W1H questions and temporal relationships","date":"2023-01-18","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/longt5-efficient-text-to-text-transformer-for","slug":"longt5-efficient-text-to-text-transformer-for","title":"LongT5: Efficient Text-To-Text Transformer for Long Sequences","date":"2021-12-15","arxiv_id":"2112.07916","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":["google-research/longt5"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/longt5-efficient-text-to-text-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2112.07916","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.07916"}}}},{"paper":"/paper/primer-pyramid-based-masked-sentence-pre","slug":"primer-pyramid-based-masked-sentence-pre","title":"PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization","date":"2021-10-16","arxiv_id":"2110.08499","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["allenai/primer"],"state":"official (archive's flag): 4 ran","n_ran":4,"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/primer-pyramid-based-masked-sentence-pre#ran","syntology_url":"https://syntology.ai/paper/2110.08499","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.08499"}}}},{"paper":"/paper/multi-document-summarization","slug":"multi-document-summarization","title":"Multi-Document Summarization withDeterminantal Point Process Attention","date":"2021-07-13","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/cross-document-language-modeling","slug":"cross-document-language-modeling","title":"CDLM: Cross-Document Language Modeling","date":"2021-01-02","arxiv_id":"2101.00406","rows_on_this_dataset":6,"code_links":2,"syntology":null},{"paper":"/paper/multi-news-a-large-scale-multi-document","slug":"multi-news-a-large-scale-multi-document","title":"Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model","date":"2019-06-04","arxiv_id":"1906.01749","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/bottom-up-abstractive-summarization","slug":"bottom-up-abstractive-summarization","title":"Bottom-Up Abstractive Summarization","date":"2018-08-31","arxiv_id":"1808.10792","rows_on_this_dataset":2,"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":0,"samples_ran_instrument_failed":5,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["sebastianGehrmann/bottom-up-summary"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bottom-up-abstractive-summarization#ran","syntology_url":"https://syntology.ai/paper/1808.10792","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.10792"}}}}],"papers_where_code_ran":3,"papers_where_code_ran_first_page":"/dataset/multi-news/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/multi-news/papers/ran/1","json":"/dataset/multi-news/papers/ran/1.json","rows":3}],"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":3,"samples_harvested":14,"samples_ran":13,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":9,"samples_unverified":1,"pointer_only_for_licence":1,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":3,"papers_with_a_run_with_no_instrument_failure":1,"papers_where_every_run_was_an_instrument_failure":2,"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":1,"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/multi-document-summarization-on-multi-news","since_archive":"/sota/multi-document-summarization-on-multi-news#since-judged","papers_judged":1,"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":"7a31f3c61c2129f65c6be967c54e30f85850074a1da38835bdddce95ce82ec25","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}