{"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/scrolls-standardized-comparison-over-long","title":"SCROLLS: Standardized CompaRison Over Long Language Sequences","arxiv_id":"2201.03533","date":"2022-01-10","proceeding":null,"authors":["Uri Shaham","Elad Segal","Maor Ivgi","Avia Efrat","Ori Yoran","Adi Haviv","Ankit Gupta","Wenhan Xiong","Mor Geva","Jonathan Berant","Omer Levy"],"abstract":"NLP benchmarks have largely focused on short texts, such as sentences and paragraphs, even though long texts comprise a considerable amount of natural language in the wild. We introduce SCROLLS, a suite of tasks that require reasoning over long texts. We examine existing long-text datasets, and handpick ones where the text is naturally long, while prioritizing tasks that involve synthesizing information across the input. SCROLLS contains summarization, question answering, and natural language inference tasks, covering multiple domains, including literature, science, business, and entertainment. Initial baselines, including Longformer Encoder-Decoder, indicate that there is ample room for improvement on SCROLLS. We make all datasets available in a unified text-to-text format and host a live leaderboard to facilitate research on model architecture and pretraining methods.","url_abs":"https://arxiv.org/abs/2201.03533v2","url_pdf":"https://arxiv.org/pdf/2201.03533v2.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":"scrolls-standardized-comparison-over-long","repo_url":"https://github.com/tau-nlp/scrolls","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"scrolls-standardized-comparison-over-long","repo_url":"https://github.com/mivg/sled","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"long-range-modeling","task_name":"Long-range modeling"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[{"method_slug":"adamw","method_name":"AdamW"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"longformer","method_name":"Longformer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[{"slug":"scrolls","name":"SCROLLS","full_name":"Standardized CompaRison Over Long Language Sequences"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/long-range-modeling-on-scrolls","task":"Long-range modeling","dataset":"SCROLLS","model":"LED Base","rank_in_archive_order":8,"of":13,"metrics":{"Avg.":"29.16","CNLI":"71.5","GovRep":"56.2 / 26.6 / 28.8","Nrtv":"18.5","QALT EM-T/H":"25.8 / 25.4\t","QMSum":"25.1 / 6.7 / 18.8","Qspr":"26.6","SumScr":"24.2 / 4.5 / 15.4"},"uses_additional_data":false},{"leaderboard":"/sota/long-range-modeling-on-scrolls","task":"Long-range modeling","dataset":"SCROLLS","model":"BART Base","rank_in_archive_order":9,"of":13,"metrics":{"Avg.":"29.01","CNLI":"77.4","GovRep":"47.9 / 18.6 / 22.7","Nrtv":"15.4","QALT EM-T/H":"26.0 / 25.9","QMSum":"30.2 / 8.7 / 20.7","Qspr":"26.3","SumScr":"27.2 / 4.9 / 16.7"},"uses_additional_data":false},{"leaderboard":"/sota/long-range-modeling-on-scrolls","task":"Long-range modeling","dataset":"SCROLLS","model":"Naive","rank_in_archive_order":10,"of":13,"metrics":{"Avg.":"19.35","CNLI":"66","GovRep":"45.3 / 17.9 / 20.8","Nrtv":"1.5","QALT EM-T/H":"25.2 / 26.1","QMSum":"14.2 / 2.0 / 9.3","Qspr":"3.4","SumScr":"19.6 / 1.8 / 11.0"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2201.03533","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.03533"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/tau-nlp/scrolls","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mivg/sled","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"unverified":6},"by_repo_kind":{"official":{"samples":8,"ran":2,"repositories":1}},"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":0,"samples":[{"code_sha256_prefix":"04757364abe8941b","entry":"get_metrics_filename","repo":"tau-nlp/scrolls","repo_kind":"official","path":"evaluator/dataset_evaluator.py","file_url":"https://github.com/tau-nlp/scrolls/blob/HEAD/evaluator/dataset_evaluator.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"04757364abe8941b"}},{"code_sha256_prefix":"52aaf6f9e86c2add","entry":"safe_read_csv","repo":"tau-nlp/scrolls","repo_kind":"official","path":"evaluator/benchmark_evaluator.py","file_url":"https://github.com/tau-nlp/scrolls/blob/HEAD/evaluator/benchmark_evaluator.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"52aaf6f9e86c2add"}},{"code_sha256_prefix":"abbee6221df98330","entry":"drop_duplicates_in_input","repo":"tau-nlp/scrolls","repo_kind":"official","path":"evaluator/dataset_evaluator.py","file_url":"https://github.com/tau-nlp/scrolls/blob/HEAD/evaluator/dataset_evaluator.py","link_basis":"harvester_set","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":"abbee6221df98330"}},{"code_sha256_prefix":"357bcaff2fb41a9f","entry":"gen","repo":"tau-nlp/scrolls","repo_kind":"official","path":"baselines/src/utils/namegenerator.py","file_url":"https://github.com/tau-nlp/scrolls/blob/HEAD/baselines/src/utils/namegenerator.py","link_basis":"harvester_set","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":"357bcaff2fb41a9f"}},{"code_sha256_prefix":"54fc256b1ee469e2","entry":"load_predictions_df","repo":"tau-nlp/scrolls","repo_kind":"official","path":"evaluator/benchmark_evaluator.py","file_url":"https://github.com/tau-nlp/scrolls/blob/HEAD/evaluator/benchmark_evaluator.py","link_basis":"harvester_set","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":"54fc256b1ee469e2"}},{"code_sha256_prefix":"4c69d00f97bf6280","entry":"merge","repo":"tau-nlp/scrolls","repo_kind":"official","path":"baselines/src/utils/config.py","file_url":"https://github.com/tau-nlp/scrolls/blob/HEAD/baselines/src/utils/config.py","link_basis":"harvester_set","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":"4c69d00f97bf6280"}},{"code_sha256_prefix":"3de4ac2599cef7ad","entry":"replace_recursive","repo":"tau-nlp/scrolls","repo_kind":"official","path":"baselines/src/utils/config.py","file_url":"https://github.com/tau-nlp/scrolls/blob/HEAD/baselines/src/utils/config.py","link_basis":"harvester_set","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":"3de4ac2599cef7ad"}},{"code_sha256_prefix":"225dafec388f7a2f","entry":"unflatten","repo":"tau-nlp/scrolls","repo_kind":"official","path":"baselines/src/utils/config.py","file_url":"https://github.com/tau-nlp/scrolls/blob/HEAD/baselines/src/utils/config.py","link_basis":"harvester_set","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":"225dafec388f7a2f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}