{"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/samsum-corpus","name":"SAMSum","full_name":null,"description_markdown":"A new dataset with abstractive dialogue summaries.\r\n\r\nSource: [SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization](/paper/samsum-corpus-a-human-annotated-dialogue-1)","description_withheld":null,"homepage":"https://arxiv.org/src/1911.12237v2/anc","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/samsum-corpus-a-human-annotated-dialogue-1","title":"SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization","first_author":"Bogdan Gliwa","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":"Federated Learning","url":"/task/federated-learning","datasets_with_task":"/datasets/task/federated-learning"},{"name":"Summarization","url":"/task/summarization","datasets_with_task":"/datasets/task/summarization"},{"name":"dialogue summary","url":"/task/dialogue-summary","datasets_with_task":"/datasets/task/dialogue-summary"},{"name":"Abstractive Dialogue Summarization","url":"/task/abstractive-dialogue-summarization","datasets_with_task":"/datasets/task/abstractive-dialogue-summarization"}],"languages":[],"variants":["SAMSum","SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization","SAMSum Corpus (translated to Russian)"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Samsung/samsum","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/samsum","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/supermario/dt-random-2.3","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/knkarthick/xsum","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/knkarthick/samsum","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/fiellin/abcdsamsumid","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/fiellin/abcsamsum","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Axel578/mydt","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/hopkiz/samsum","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/samsum","frameworks":["tf","jax"]}],"num_papers_in_archive":145,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-summarization-on-samsum-corpus","task":"Text Summarization","dataset_variant":"SAMSum","rows":12,"metrics":["ROUGE-1","ROUGE-2","ROUGE-L","BertScoreF1"],"first_row_in_archive_order":{"model":"OmniVec2","paper":"/paper/omnivec2-a-novel-transformer-based-network","metrics":{"BertScoreF1":"65.1","ROUGE-1":"59.1","ROUGE-2":"34.1","ROUGE-L":"63.7"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/abstractive-text-summarization-on-samsum","task":"Abstractive Text Summarization","dataset_variant":"SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization","rows":0,"metrics":["Test ROUGE-1","Test ROUGE-2","Test ROUGE-L","Validation ROUGE-1","Validation ROUGE-2","Validation ROUGE-L"],"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-samsum-1","task":"Summarization","dataset_variant":"SAMSum","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"},{"leaderboard":"/sota/summarization-on-samsum-corpus-a-human","task":"Summarization","dataset_variant":"SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization","rows":0,"metrics":["Test ROGUE-1","Test ROGUE-2","Test ROGUE-L","Validation ROGUE-1","Validation ROGUE-2","Validation ROGUE-L"],"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":10,"of":10,"counts":{"papers_with_a_benchmark_row":10,"with_a_code_link":6,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":10,"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":[{"paper":"/paper/crispo-multi-aspect-critique-suggestion","slug":"crispo-multi-aspect-critique-suggestion","title":"CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text Generation","date":"2024-10-03","arxiv_id":"2410.02748","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/salient-information-prompting-to-steer","slug":"salient-information-prompting-to-steer","title":"Salient Information Prompting to Steer Content in Prompt-based Abstractive Summarization","date":"2024-10-03","arxiv_id":"2410.02741","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hierarchical-prompting-taxonomy-a-universal","slug":"hierarchical-prompting-taxonomy-a-universal","title":"Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models Aligned with Human Cognitive Principles","date":"2024-06-18","arxiv_id":"2406.12644","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/omnivec2-a-novel-transformer-based-network","slug":"omnivec2-a-novel-transformer-based-network","title":"OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","date":"2024-01-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/instructive-dialogue-summarization-with-query","slug":"instructive-dialogue-summarization-with-query","title":"Instructive Dialogue Summarization with Query Aggregations","date":"2023-10-17","arxiv_id":"2310.10981","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/momentum-calibration-for-text-generation","slug":"momentum-calibration-for-text-generation","title":"Momentum Calibration for Text Generation","date":"2022-12-08","arxiv_id":"2212.04257","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/calibrating-sequence-likelihood-improves","slug":"calibrating-sequence-likelihood-improves","title":"Calibrating Sequence likelihood Improves Conditional Language Generation","date":"2022-09-30","arxiv_id":"2210.00045","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/mind-the-gap-injecting-commonsense-knowledge","slug":"mind-the-gap-injecting-commonsense-knowledge","title":"Mind the Gap! Injecting Commonsense Knowledge for Abstractive Dialogue Summarization","date":"2022-09-02","arxiv_id":"2209.00930","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/topic-aware-contrastive-learning-for","slug":"topic-aware-contrastive-learning-for","title":"Topic-Aware Contrastive Learning for Abstractive Dialogue Summarization","date":"2021-09-10","arxiv_id":"2109.04994","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"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":2,"code_links":0,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/crispo-multi-aspect-critique-suggestion","slug":"crispo-multi-aspect-critique-suggestion","title":"CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text Generation","date":"2024-10-03","arxiv_id":"2410.02748","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/salient-information-prompting-to-steer","slug":"salient-information-prompting-to-steer","title":"Salient Information Prompting to Steer Content in Prompt-based Abstractive Summarization","date":"2024-10-03","arxiv_id":"2410.02741","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hierarchical-prompting-taxonomy-a-universal","slug":"hierarchical-prompting-taxonomy-a-universal","title":"Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models Aligned with Human Cognitive Principles","date":"2024-06-18","arxiv_id":"2406.12644","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/omnivec2-a-novel-transformer-based-network","slug":"omnivec2-a-novel-transformer-based-network","title":"OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","date":"2024-01-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/instructive-dialogue-summarization-with-query","slug":"instructive-dialogue-summarization-with-query","title":"Instructive Dialogue Summarization with Query Aggregations","date":"2023-10-17","arxiv_id":"2310.10981","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/momentum-calibration-for-text-generation","slug":"momentum-calibration-for-text-generation","title":"Momentum Calibration for Text Generation","date":"2022-12-08","arxiv_id":"2212.04257","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/calibrating-sequence-likelihood-improves","slug":"calibrating-sequence-likelihood-improves","title":"Calibrating Sequence likelihood Improves Conditional Language Generation","date":"2022-09-30","arxiv_id":"2210.00045","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/mind-the-gap-injecting-commonsense-knowledge","slug":"mind-the-gap-injecting-commonsense-knowledge","title":"Mind the Gap! Injecting Commonsense Knowledge for Abstractive Dialogue Summarization","date":"2022-09-02","arxiv_id":"2209.00930","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/topic-aware-contrastive-learning-for","slug":"topic-aware-contrastive-learning-for","title":"Topic-Aware Contrastive Learning for Abstractive Dialogue Summarization","date":"2021-09-10","arxiv_id":"2109.04994","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"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":2,"code_links":0,"syntology":null}],"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":"1185f76f4540573f0f25f40f5327c5d5070c9e74b16f45840695dce01b8efb01","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}