{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/tldr-extreme-summarization-of-scientific","title":"TLDR: Extreme Summarization of Scientific Documents","arxiv_id":"2004.15011","date":"2020-04-30","proceeding":"Findings of the Association for Computational Linguistics 2020","authors":["Isabel Cachola","Kyle Lo","Arman Cohan","Daniel S. Weld"],"abstract":"We introduce TLDR generation, a new form of extreme summarization, for scientific papers. TLDR generation involves high source compression and requires expert background knowledge and understanding of complex domain-specific language. To facilitate study on this task, we introduce SciTLDR, a new multi-target dataset of 5.4K TLDRs over 3.2K papers. SciTLDR contains both author-written and expert-derived TLDRs, where the latter are collected using a novel annotation protocol that produces high-quality summaries while minimizing annotation burden. We propose CATTS, a simple yet effective learning strategy for generating TLDRs that exploits titles as an auxiliary training signal. CATTS improves upon strong baselines under both automated metrics and human evaluations. Data and code are publicly available at https://github.com/allenai/scitldr.","url_abs":"https://arxiv.org/abs/2004.15011v3","url_pdf":"https://arxiv.org/pdf/2004.15011v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"tldr-extreme-summarization-of-scientific","repo_url":"https://github.com/allenai/scitldr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"tldr-extreme-summarization-of-scientific","repo_url":"https://github.com/bnitsan/papertweet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"tldr-extreme-summarization-of-scientific","repo_url":"https://github.com/iamgroot42/mimir","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"tldr-extreme-summarization-of-scientific","repo_url":"https://github.com/jungokasai/twist_decoding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"abstractive-text-summarization","task_name":"Abstractive Text Summarization"},{"task_slug":"extreme-summarization","task_name":"Extreme Summarization"}],"methods":[],"datasets_introduced":[{"slug":"scitldr","name":"SciTLDR","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2004.15011","atlas_url":"https://app.syntology.ai/?focus=2004.15011","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.15011"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bnitsan/papertweet","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/allenai/scitldr","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/iamgroot42/mimir","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jungokasai/twist_decoding","reach":null}],"summary":{"ran":4,"ran_draft_wrong":7,"ran_honours":4,"unverified":4},"by_repo_kind":{"official":{"samples":5,"ran":3,"repositories":1},"listed":{"samples":14,"ran":12,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":4,"samples":[{"code_sha256_prefix":"c1e87177e1879e25","entry":"CustomDataset","repo":"bnitsan/papertweet","repo_kind":"listed","path":"models/model.py","file_url":"https://github.com/bnitsan/papertweet/blob/HEAD/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c1e87177e1879e25"}},{"code_sha256_prefix":"5a617f87118cdcb7","entry":"add_eos_token_to_target","repo":"bnitsan/papertweet","repo_kind":"listed","path":"models/model.py","file_url":"https://github.com/bnitsan/papertweet/blob/HEAD/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5a617f87118cdcb7"}},{"code_sha256_prefix":"a6e6d89d8756add2","entry":"add_prompt_to_source","repo":"bnitsan/papertweet","repo_kind":"listed","path":"models/model.py","file_url":"https://github.com/bnitsan/papertweet/blob/HEAD/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a6e6d89d8756add2"}},{"code_sha256_prefix":"c62c9d8fca3d91e9","entry":"build_batches","repo":"allenai/scitldr","repo_kind":"official","path":"SciTLDR-Data/to_stories.py","file_url":"https://github.com/allenai/scitldr/blob/HEAD/SciTLDR-Data/to_stories.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c62c9d8fca3d91e9"}},{"code_sha256_prefix":"4f101059eeab11c8","entry":"get_line_ids","repo":"jungokasai/twist_decoding","repo_kind":"listed","path":"fairseq/twist/generate_twist_tldr.py","file_url":"https://github.com/jungokasai/twist_decoding/blob/HEAD/fairseq/twist/generate_twist_tldr.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4f101059eeab11c8"}},{"code_sha256_prefix":"39d9cd45b8edce68","entry":"get_num_train_steps","repo":"bnitsan/papertweet","repo_kind":"listed","path":"models/model.py","file_url":"https://github.com/bnitsan/papertweet/blob/HEAD/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"39d9cd45b8edce68"}},{"code_sha256_prefix":"cb94a51b64280335","entry":"get_train_dataloaders","repo":"bnitsan/papertweet","repo_kind":"listed","path":"models/model.py","file_url":"https://github.com/bnitsan/papertweet/blob/HEAD/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cb94a51b64280335"}},{"code_sha256_prefix":"238977a0b4ed33b4","entry":"get_val_dataloaders","repo":"bnitsan/papertweet","repo_kind":"listed","path":"models/model.py","file_url":"https://github.com/bnitsan/papertweet/blob/HEAD/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"238977a0b4ed33b4"}},{"code_sha256_prefix":"2ed659a3dd835939","entry":"hashhex","repo":"allenai/scitldr","repo_kind":"official","path":"SciTLDR-Data/make_datafiles.py","file_url":"https://github.com/allenai/scitldr/blob/HEAD/SciTLDR-Data/make_datafiles.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2ed659a3dd835939"}},{"code_sha256_prefix":"18e9681c72c82d0d","entry":"jaccard","repo":"bnitsan/papertweet","repo_kind":"listed","path":"models/model.py","file_url":"https://github.com/bnitsan/papertweet/blob/HEAD/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"18e9681c72c82d0d"}},{"code_sha256_prefix":"258d4a4b0a8b6b16","entry":"pad_candidates","repo":"jungokasai/twist_decoding","repo_kind":"listed","path":"fairseq/twist/generate_twist_tldr.py","file_url":"https://github.com/jungokasai/twist_decoding/blob/HEAD/fairseq/twist/generate_twist_tldr.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"258d4a4b0a8b6b16"}},{"code_sha256_prefix":"53d5b85264377a72","entry":"read_input","repo":"jungokasai/twist_decoding","repo_kind":"listed","path":"fairseq/twist/generate_twist_tldr.py","file_url":"https://github.com/jungokasai/twist_decoding/blob/HEAD/fairseq/twist/generate_twist_tldr.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"53d5b85264377a72"}},{"code_sha256_prefix":"8175760b8eddec2b","entry":"read_text_file","repo":"allenai/scitldr","repo_kind":"official","path":"SciTLDR-Data/make_datafiles.py","file_url":"https://github.com/allenai/scitldr/blob/HEAD/SciTLDR-Data/make_datafiles.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8175760b8eddec2b"}},{"code_sha256_prefix":"9447eeb9dbba8819","entry":"rouge_score","repo":"bnitsan/papertweet","repo_kind":"listed","path":"models/model.py","file_url":"https://github.com/bnitsan/papertweet/blob/HEAD/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9447eeb9dbba8819"}},{"code_sha256_prefix":"f6ceffd4a0becc2a","entry":"train_val_test_path","repo":"bnitsan/papertweet","repo_kind":"listed","path":"models/model.py","file_url":"https://github.com/bnitsan/papertweet/blob/HEAD/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f6ceffd4a0becc2a"}},{"code_sha256_prefix":"0e0ae26c9368468f","entry":"CondGenModel","repo":"bnitsan/papertweet","repo_kind":"listed","path":"models/model.py","file_url":"https://github.com/bnitsan/papertweet/blob/HEAD/models/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0e0ae26c9368468f"}},{"code_sha256_prefix":"34369269378d0047","entry":"add_ctrl","repo":"allenai/scitldr","repo_kind":"official","path":"SciTLDR-Data/build_ctrl_datasets.py","file_url":"https://github.com/allenai/scitldr/blob/HEAD/SciTLDR-Data/build_ctrl_datasets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"34369269378d0047"}},{"code_sha256_prefix":"bba331b9f86f6008","entry":"generate_TLDRs","repo":"jungokasai/twist_decoding","repo_kind":"listed","path":"fairseq/twist/generate_twist_tldr.py","file_url":"https://github.com/jungokasai/twist_decoding/blob/HEAD/fairseq/twist/generate_twist_tldr.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bba331b9f86f6008"}},{"code_sha256_prefix":"478f0055455e2023","entry":"get_url_hashes","repo":"allenai/scitldr","repo_kind":"official","path":"SciTLDR-Data/make_datafiles.py","file_url":"https://github.com/allenai/scitldr/blob/HEAD/SciTLDR-Data/make_datafiles.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"478f0055455e2023"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}