{"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/xsum","name":"XSum","full_name":null,"description_markdown":"The Extreme Summarization (**XSum**) dataset is a dataset for evaluation of abstractive single-document summarization systems. The goal is to create a short, one-sentence new summary answering the question “What is the article about?”. The dataset consists of 226,711 news articles accompanied with a one-sentence summary. The articles are collected from BBC articles (2010 to 2017) and cover a wide variety of domains (e.g., News, Politics, Sports, Weather, Business, Technology, Science, Health, Family, Education, Entertainment and Arts). The official random split contains 204,045 (90%), 11,332 (5%) and 11,334 (5) documents in training, validation and test sets, respectively.\n\nSource: [https://arxiv.org/pdf/1808.08745.pdf](https://arxiv.org/pdf/1808.08745.pdf)\nImage Source: [https://arxiv.org/pdf/1808.08745.pdf](https://arxiv.org/pdf/1808.08745.pdf)","description_withheld":null,"homepage":"https://github.com/EdinburghNLP/XSum/tree/master/XSum-Dataset","introduced_date":"2018-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/dont-give-me-the-details-just-the-summary","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","first_author":"Shashi Narayan","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Summarization","url":"/task/text-summarization","datasets_with_task":"/datasets/task/text-summarization"},{"name":"Abstractive Text Summarization","url":"/task/abstractive-text-summarization","datasets_with_task":"/datasets/task/abstractive-text-summarization"},{"name":"Sequence-to-sequence Language Modeling","url":"/task/sequence-to-sequence-language-modeling","datasets_with_task":"/datasets/task/sequence-to-sequence-language-modeling"},{"name":"Summarization","url":"/task/summarization","datasets_with_task":"/datasets/task/summarization"},{"name":"Extreme Summarization","url":"/task/extreme-summarization","datasets_with_task":"/datasets/task/extreme-summarization"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["XSum","X-Sum"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/talgatzh/xfinetuning1","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/xsum","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/talgatzh/xsum-kk3","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/shalinik/xsum","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/lewtun/autoevaluate__xsum","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/polinaeterna/xsum","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/EdinburghNLP/xsum","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/xsum","frameworks":["tf","jax"]},{"repo":"https://github.com/EdinburghNLP/XSum","url":"https://github.com/EdinburghNLP/XSum","frameworks":["pytorch"]}],"num_papers_in_archive":32,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-summarization-on-x-sum","task":"Text Summarization","dataset_variant":"X-Sum","rows":18,"metrics":["ROUGE-1","ROUGE-2","ROUGE-3","ROUGE-L"],"first_row_in_archive_order":{"model":"Selfmem","paper":"/paper/lift-yourself-up-retrieval-augmented-text","metrics":{"ROUGE-1":"50.30","ROUGE-2":"26.70","ROUGE-3":"41.60"},"code_links":[{"title":"hannibal046/selfmemory","url":"https://github.com/hannibal046/selfmemory"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/extreme-summarization-on-xsum","task":"Extreme Summarization","dataset_variant":"XSum","rows":1,"metrics":["METEOR"],"first_row_in_archive_order":{"model":"PEGASUS","paper":"/paper/the-gem-benchmark-natural-language-generation","metrics":{"METEOR":"0.216"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-summarization-on-xsum-2","task":"Text Summarization","dataset_variant":"XSum","rows":1,"metrics":["ROUGE-1"],"first_row_in_archive_order":{"model":"SRformer-BART","paper":"/paper/segmented-recurrent-transformer-an-efficient","metrics":{"ROUGE-1":"39.02"},"code_links":[{"title":"yinghanlong/SRtransformer","url":"https://github.com/yinghanlong/SRtransformer"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/abstractive-text-summarization-on-xsum","task":"Abstractive Text Summarization","dataset_variant":"XSum","rows":0,"metrics":["Test ROGUE-1","Test ROGUE-2","Test ROGUE-L","Test ROGUE-Lsum","Validation ROGUE-1","Validation ROGUE-2","Validation ROGUE-L","Validation ROGUE-Lsum"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/summarization-on-xsum","task":"Summarization","dataset_variant":"XSum","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":12,"of":12,"counts":{"papers_with_a_benchmark_row":12,"with_a_code_link":10,"where_syntology_ran_a_sample":8,"not_listed_spam_title":0,"listed":12,"listed_where_code_ran":8,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":7,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":7,"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/segmented-recurrent-transformer-an-efficient","slug":"segmented-recurrent-transformer-an-efficient","title":"Segmented Recurrent Transformer: An Efficient Sequence-to-Sequence Model","date":"2023-05-24","arxiv_id":"2305.16340","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/palm-2-technical-report-1","slug":"palm-2-technical-report-1","title":"PaLM 2 Technical Report","date":"2023-05-17","arxiv_id":"2305.10403","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/lift-yourself-up-retrieval-augmented-text","slug":"lift-yourself-up-retrieval-augmented-text","title":"Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory","date":"2023-05-03","arxiv_id":"2305.02437","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":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["hannibal046/selfmemory"],"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/lift-yourself-up-retrieval-augmented-text#ran","syntology_url":"https://syntology.ai/paper/2305.02437","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.02437"}}}},{"paper":"/paper/brio-bringing-order-to-abstractive","slug":"brio-bringing-order-to-abstractive","title":"BRIO: Bringing Order to Abstractive Summarization","date":"2022-03-31","arxiv_id":"2203.16804","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["yixinl7/brio"],"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/brio-bringing-order-to-abstractive#ran","syntology_url":"https://syntology.ai/paper/2203.16804","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.16804"}}}},{"paper":"/paper/summareranker-a-multi-task-mixture-of-experts-1","slug":"summareranker-a-multi-task-mixture-of-experts-1","title":"SummaReranker: A Multi-Task Mixture-of-Experts Re-ranking Framework for Abstractive Summarization","date":"2022-03-13","arxiv_id":"2203.06569","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["ntunlp/summareranker"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/summareranker-a-multi-task-mixture-of-experts-1#ran","syntology_url":"https://syntology.ai/paper/2203.06569","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.06569"}}}},{"paper":"/paper/simcls-a-simple-framework-for-contrastive","slug":"simcls-a-simple-framework-for-contrastive","title":"SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization","date":"2021-06-03","arxiv_id":"2106.01890","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":3,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["yixinL7/SimCLS"],"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/simcls-a-simple-framework-for-contrastive#ran","syntology_url":"https://syntology.ai/paper/2106.01890","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.01890"}}}},{"paper":"/paper/hierarchical-learning-for-generation-with","slug":"hierarchical-learning-for-generation-with","title":"Hierarchical Learning for Generation with Long Source Sequences","date":"2021-04-15","arxiv_id":"2104.07545","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/the-gem-benchmark-natural-language-generation","slug":"the-gem-benchmark-natural-language-generation","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","date":"2021-02-02","arxiv_id":"2102.01672","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/pegasus-pre-training-with-extracted-gap","slug":"pegasus-pre-training-with-extracted-gap","title":"PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization","date":"2019-12-18","arxiv_id":"1912.08777","rows_on_this_dataset":1,"code_links":19,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":19,"samples_ran":16,"samples_constructed":0,"samples_ran_checked":15,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["google-research/pegasus"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pegasus-pre-training-with-extracted-gap#ran","syntology_url":"https://syntology.ai/paper/1912.08777","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.08777"}}}},{"paper":"/paper/bart-denoising-sequence-to-sequence-pre","slug":"bart-denoising-sequence-to-sequence-pre","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","date":"2019-10-29","arxiv_id":"1910.13461","rows_on_this_dataset":1,"code_links":47,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":53,"samples_ran":40,"samples_constructed":7,"samples_ran_checked":30,"samples_ran_instrument_failed":10,"samples_unverified":13,"pointer_only_for_licence":13,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bart-denoising-sequence-to-sequence-pre#ran","syntology_url":"https://syntology.ai/paper/1910.13461","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.13461"}}}},{"paper":"/paper/text-summarization-with-pretrained-encoders","slug":"text-summarization-with-pretrained-encoders","title":"Text Summarization with Pretrained Encoders","date":"2019-08-22","arxiv_id":"1908.08345","rows_on_this_dataset":1,"code_links":19,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":13,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":3,"samples_unverified":8,"pointer_only_for_licence":5,"official":{"repos":["nlpyang/PreSumm"],"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/text-summarization-with-pretrained-encoders#ran","syntology_url":"https://syntology.ai/paper/1908.08345","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.08345"}}}},{"paper":"/paper/dont-give-me-the-details-just-the-summary","slug":"dont-give-me-the-details-just-the-summary","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","date":"2018-08-27","arxiv_id":"1808.08745","rows_on_this_dataset":7,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["shashiongithub/XSum"],"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/dont-give-me-the-details-just-the-summary#ran","syntology_url":"https://syntology.ai/paper/1808.08745","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.08745"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/segmented-recurrent-transformer-an-efficient","slug":"segmented-recurrent-transformer-an-efficient","title":"Segmented Recurrent Transformer: An Efficient Sequence-to-Sequence Model","date":"2023-05-24","arxiv_id":"2305.16340","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/palm-2-technical-report-1","slug":"palm-2-technical-report-1","title":"PaLM 2 Technical Report","date":"2023-05-17","arxiv_id":"2305.10403","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/lift-yourself-up-retrieval-augmented-text","slug":"lift-yourself-up-retrieval-augmented-text","title":"Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory","date":"2023-05-03","arxiv_id":"2305.02437","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":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["hannibal046/selfmemory"],"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/lift-yourself-up-retrieval-augmented-text#ran","syntology_url":"https://syntology.ai/paper/2305.02437","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.02437"}}}},{"paper":"/paper/brio-bringing-order-to-abstractive","slug":"brio-bringing-order-to-abstractive","title":"BRIO: Bringing Order to Abstractive Summarization","date":"2022-03-31","arxiv_id":"2203.16804","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["yixinl7/brio"],"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/brio-bringing-order-to-abstractive#ran","syntology_url":"https://syntology.ai/paper/2203.16804","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.16804"}}}},{"paper":"/paper/summareranker-a-multi-task-mixture-of-experts-1","slug":"summareranker-a-multi-task-mixture-of-experts-1","title":"SummaReranker: A Multi-Task Mixture-of-Experts Re-ranking Framework for Abstractive Summarization","date":"2022-03-13","arxiv_id":"2203.06569","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["ntunlp/summareranker"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/summareranker-a-multi-task-mixture-of-experts-1#ran","syntology_url":"https://syntology.ai/paper/2203.06569","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.06569"}}}},{"paper":"/paper/simcls-a-simple-framework-for-contrastive","slug":"simcls-a-simple-framework-for-contrastive","title":"SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization","date":"2021-06-03","arxiv_id":"2106.01890","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":3,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["yixinL7/SimCLS"],"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/simcls-a-simple-framework-for-contrastive#ran","syntology_url":"https://syntology.ai/paper/2106.01890","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.01890"}}}},{"paper":"/paper/hierarchical-learning-for-generation-with","slug":"hierarchical-learning-for-generation-with","title":"Hierarchical Learning for Generation with Long Source Sequences","date":"2021-04-15","arxiv_id":"2104.07545","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/the-gem-benchmark-natural-language-generation","slug":"the-gem-benchmark-natural-language-generation","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","date":"2021-02-02","arxiv_id":"2102.01672","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/pegasus-pre-training-with-extracted-gap","slug":"pegasus-pre-training-with-extracted-gap","title":"PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization","date":"2019-12-18","arxiv_id":"1912.08777","rows_on_this_dataset":1,"code_links":19,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":19,"samples_ran":16,"samples_constructed":0,"samples_ran_checked":15,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["google-research/pegasus"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pegasus-pre-training-with-extracted-gap#ran","syntology_url":"https://syntology.ai/paper/1912.08777","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.08777"}}}},{"paper":"/paper/bart-denoising-sequence-to-sequence-pre","slug":"bart-denoising-sequence-to-sequence-pre","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","date":"2019-10-29","arxiv_id":"1910.13461","rows_on_this_dataset":1,"code_links":47,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":53,"samples_ran":40,"samples_constructed":7,"samples_ran_checked":30,"samples_ran_instrument_failed":10,"samples_unverified":13,"pointer_only_for_licence":13,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bart-denoising-sequence-to-sequence-pre#ran","syntology_url":"https://syntology.ai/paper/1910.13461","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.13461"}}}},{"paper":"/paper/text-summarization-with-pretrained-encoders","slug":"text-summarization-with-pretrained-encoders","title":"Text Summarization with Pretrained Encoders","date":"2019-08-22","arxiv_id":"1908.08345","rows_on_this_dataset":1,"code_links":19,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":13,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":3,"samples_unverified":8,"pointer_only_for_licence":5,"official":{"repos":["nlpyang/PreSumm"],"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/text-summarization-with-pretrained-encoders#ran","syntology_url":"https://syntology.ai/paper/1908.08345","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.08345"}}}},{"paper":"/paper/dont-give-me-the-details-just-the-summary","slug":"dont-give-me-the-details-just-the-summary","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","date":"2018-08-27","arxiv_id":"1808.08745","rows_on_this_dataset":7,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["shashiongithub/XSum"],"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/dont-give-me-the-details-just-the-summary#ran","syntology_url":"https://syntology.ai/paper/1808.08745","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.08745"}}}}],"papers_where_code_ran":8,"papers_where_code_ran_first_page":"/dataset/xsum/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/xsum/papers/ran/1","json":"/dataset/xsum/papers/ran/1.json","rows":8}],"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":8,"samples_harvested":117,"samples_ran":87,"samples_constructed":12,"samples_ran_checked":72,"samples_ran_instrument_failed":15,"samples_unverified":30,"pointer_only_for_licence":20,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":8,"papers_with_a_run_with_no_instrument_failure":7,"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":4,"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/text-summarization-on-x-sum","since_archive":"/sota/text-summarization-on-x-sum#since-judged","papers_judged":4,"placed":0},{"leaderboard":"/sota/text-summarization-on-xsum-2","since_archive":"/sota/text-summarization-on-xsum-2#since-judged","papers_judged":3,"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":"e6e476ffd3e8c771abb3b06dc16290d0c56ec84b1a82988d80968b59eb6bf1ca","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}