{"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/big-bird-transformers-for-longer-sequences","title":"Big Bird: Transformers for Longer Sequences","arxiv_id":"2007.14062","date":"2020-07-28","proceeding":"NeurIPS 2020 12","authors":["Manzil Zaheer","Guru Guruganesh","Avinava Dubey","Joshua Ainslie","Chris Alberti","Santiago Ontanon","Philip Pham","Anirudh Ravula","Qifan Wang","Li Yang","Amr Ahmed"],"abstract":"Transformers-based models, such as BERT, have been one of the most successful deep learning models for NLP. Unfortunately, one of their core limitations is the quadratic dependency (mainly in terms of memory) on the sequence length due to their full attention mechanism. To remedy this, we propose, BigBird, a sparse attention mechanism that reduces this quadratic dependency to linear. We show that BigBird is a universal approximator of sequence functions and is Turing complete, thereby preserving these properties of the quadratic, full attention model. Along the way, our theoretical analysis reveals some of the benefits of having $O(1)$ global tokens (such as CLS), that attend to the entire sequence as part of the sparse attention mechanism. The proposed sparse attention can handle sequences of length up to 8x of what was previously possible using similar hardware. As a consequence of the capability to handle longer context, BigBird drastically improves performance on various NLP tasks such as question answering and summarization. We also propose novel applications to genomics data.","url_abs":"https://arxiv.org/abs/2007.14062v2","url_pdf":"https://arxiv.org/pdf/2007.14062v2.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":"big-bird-transformers-for-longer-sequences","repo_url":"https://github.com/google-research/bigbird","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"big-bird-transformers-for-longer-sequences","repo_url":"https://github.com/facebookresearch/xformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"big-bird-transformers-for-longer-sequences","repo_url":"https://github.com/huggingface/transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"big-bird-transformers-for-longer-sequences","repo_url":"https://github.com/mim-solutions/bert_for_longer_texts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"big-bird-transformers-for-longer-sequences","repo_url":"https://github.com/mim-solutions/roberta_for_longer_texts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"big-bird-transformers-for-longer-sequences","repo_url":"https://github.com/monologg/kobigbird","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"big-bird-transformers-for-longer-sequences","repo_url":"https://github.com/sajjjadayobi/ParsBigBird","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"AGPL-3.0"}},{"paper_slug":"big-bird-transformers-for-longer-sequences","repo_url":"https://github.com/sergeykramp/mthesis-bigbird-embeddings","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"big-bird-transformers-for-longer-sequences","repo_url":"https://github.com/thefonseca/factorsum","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"big-bird-transformers-for-longer-sequences","repo_url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/big_bird","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"big-bird-transformers-for-longer-sequences","repo_url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/paddlenlp/transformers/bigbird","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null},{"paper_slug":"big-bird-transformers-for-longer-sequences","repo_url":"https://github.com/pwc-1/Paper-8/tree/main/big_bird","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"big-bird-transformers-for-longer-sequences","repo_url":"https://github.com/pwc-1/Paper-8/tree/main/bigbird_pegasus","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"big-bird-transformers-for-longer-sequences","repo_url":"https://github.com/tensorflow/models/tree/master/official/nlp/projects/bigbird","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"linguistic-acceptability","task_name":"Linguistic Acceptability"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"text-summarization","task_name":"Text Summarization"}],"methods":[{"method_slug":"bigbird","method_name":"BigBird"}],"datasets_introduced":[],"methods_introduced":[{"slug":"bigbird","name":"BigBird","full_name":"BigBird"}],"results":[{"leaderboard":"/sota/document-summarization-on-bbc-xsum","task":"Document Summarization","dataset":"BBC XSum","model":"BigBird-Pegasus","rank_in_archive_order":1,"of":1,"metrics":{"ROUGE-1":"47.12","ROUGE-2":"24.05","ROUGE-L":"38.8"},"uses_additional_data":false},{"leaderboard":"/sota/document-summarization-on-cnn-daily-mail","task":"Document Summarization","dataset":"CNN / Daily Mail","model":"BigBird-Pegasus","rank_in_archive_order":10,"of":26,"metrics":{"ROUGE-1":"43.84","ROUGE-2":"21.11","ROUGE-L":"40.74"},"uses_additional_data":false},{"leaderboard":"/sota/linguistic-acceptability-on-cola","task":"Linguistic Acceptability","dataset":"CoLA","model":"BigBird","rank_in_archive_order":32,"of":43,"metrics":{"Accuracy":"58.5%"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-multinli","task":"Natural Language Inference","dataset":"MultiNLI","model":"BigBird","rank_in_archive_order":22,"of":67,"metrics":{"Matched":"87.5"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-qnli","task":"Natural Language Inference","dataset":"QNLI","model":"BigBird","rank_in_archive_order":26,"of":43,"metrics":{"Accuracy":"92.2%"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-rte","task":"Natural Language Inference","dataset":"RTE","model":"BigBird","rank_in_archive_order":44,"of":90,"metrics":{"Accuracy":"75.0%"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-hotpotqa","task":"Question Answering","dataset":"HotpotQA","model":"BigBird-etc","rank_in_archive_order":2,"of":72,"metrics":{"ANS-F1":"0.755","JOINT-F1":"0.736","SUP-F1":"0.891"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-quora-question-pairs","task":"Question Answering","dataset":"Quora Question Pairs","model":"BigBird","rank_in_archive_order":15,"of":19,"metrics":{"Accuracy":"88.6%"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-triviaqa","task":"Question Answering","dataset":"TriviaQA","model":"BigBird-etc","rank_in_archive_order":49,"of":56,"metrics":{"F1":"80.9"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-wikihop","task":"Question Answering","dataset":"WikiHop","model":"BigBird-etc","rank_in_archive_order":1,"of":9,"metrics":{"Test":"82.3"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-mrpc","task":"Semantic Textual Similarity","dataset":"MRPC","model":"BigBird","rank_in_archive_order":38,"of":45,"metrics":{"F1":"91.5"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts-benchmark","task":"Semantic Textual Similarity","dataset":"STS Benchmark","model":"BigBird","rank_in_archive_order":39,"of":66,"metrics":{"Spearman Correlation":".878"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-sst-2-binary","task":"Sentiment Analysis","dataset":"SST-2 Binary classification","model":"BigBird","rank_in_archive_order":34,"of":87,"metrics":{"Accuracy":"94.6"},"uses_additional_data":false},{"leaderboard":"/sota/text-classification-on-arxiv","task":"Text Classification","dataset":"Arxiv HEP-TH citation graph","model":"BigBird","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"92.31"},"uses_additional_data":false},{"leaderboard":"/sota/text-classification-on-hyperpartisan-1","task":"Text Classification","dataset":"Hyperpartisan","model":"BigBird","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"92.2"},"uses_additional_data":false},{"leaderboard":"/sota/text-classification-on-patents","task":"Text Classification","dataset":"Patents","model":"BigBird","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"69.3"},"uses_additional_data":false},{"leaderboard":"/sota/text-classification-on-yelp-5","task":"Text Classification","dataset":"Yelp-5","model":"BigBird","rank_in_archive_order":3,"of":7,"metrics":{"Accuracy":"72.16%"},"uses_additional_data":false},{"leaderboard":"/sota/text-summarization-on-bigpatent","task":"Text Summarization","dataset":"BigPatent","model":"BigBird-Pegasus","rank_in_archive_order":2,"of":2,"metrics":{"ROUGE-1":"60.64","ROUGE-2":"42.46","ROUGE-L":"50.01"},"uses_additional_data":false},{"leaderboard":"/sota/text-summarization-on-pubmed-1","task":"Text Summarization","dataset":"Pubmed","model":"BigBird-Pegasus","rank_in_archive_order":15,"of":29,"metrics":{"ROUGE-1":"46.32","ROUGE-2":"20.65","ROUGE-L":"42.33"},"uses_additional_data":true},{"leaderboard":"/sota/text-summarization-on-arxiv-1","task":"Text Summarization","dataset":"arXiv","model":"BigBird-Pegasus","rank_in_archive_order":1,"of":1,"metrics":{"ROUGE-1":"46.63","ROUGE-2":"19.02","ROUGE-L":"41.77"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2007.14062","atlas_url":"https://app.syntology.ai/?focus=2007.14062","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.14062"}},"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/huggingface/transformers","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mim-solutions/bert_for_longer_texts","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sergeykramp/mthesis-bigbird-embeddings","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pwc-1/Paper-8/tree/main/big_bird","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google-research/bigbird","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thefonseca/factorsum","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tensorflow/models/tree/master/official/nlp/projects/bigbird","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/monologg/kobigbird","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pwc-1/Paper-8/tree/main/bigbird_pegasus","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sajjjadayobi/ParsBigBird","reach":{"status":"ok","spdx":"AGPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/paddlenlp/transformers/bigbird","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/big_bird","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/xformers","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mim-solutions/roberta_for_longer_texts","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":1,"ran_fixture":3,"ran_draft_wrong":5,"ran_honours":1,"unverified":5},"by_repo_kind":{"official":{"samples":2,"ran":1,"repositories":1},"listed":{"samples":13,"ran":9,"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":11,"samples":[{"code_sha256_prefix":"e4b0ec678a1f3059","entry":"InconsistentSplittingParamsException","repo":"mim-solutions/bert_for_longer_texts","repo_kind":"listed","path":"belt_nlp/splitting.py","file_url":"https://github.com/mim-solutions/bert_for_longer_texts/blob/HEAD/belt_nlp/splitting.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"e4b0ec678a1f3059"}},{"code_sha256_prefix":"44d0dd1eff48b3db","entry":"create_rand_mask_from_inputs","repo":"google-research/bigbird","repo_kind":"official","path":"bigbird/core/attention.py","file_url":"https://github.com/google-research/bigbird/blob/HEAD/bigbird/core/attention.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"44d0dd1eff48b3db"}},{"code_sha256_prefix":"2c5945c3b5a80279","entry":"create_rand_mask_from_inputs","repo":"monologg/kobigbird","repo_kind":"listed","path":"pretrain/kobigbird/attention.py","file_url":"https://github.com/monologg/kobigbird/blob/HEAD/pretrain/kobigbird/attention.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2c5945c3b5a80279"}},{"code_sha256_prefix":"c91a4a5114716579","entry":"split_overlapping","repo":"mim-solutions/bert_for_longer_texts","repo_kind":"listed","path":"belt_nlp/splitting.py","file_url":"https://github.com/mim-solutions/bert_for_longer_texts/blob/HEAD/belt_nlp/splitting.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"c91a4a5114716579"}},{"code_sha256_prefix":"0ce3135e26fafb14","entry":"split_tokens_into_smaller_chunks","repo":"mim-solutions/bert_for_longer_texts","repo_kind":"listed","path":"belt_nlp/splitting.py","file_url":"https://github.com/mim-solutions/bert_for_longer_texts/blob/HEAD/belt_nlp/splitting.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"0ce3135e26fafb14"}},{"code_sha256_prefix":"15b2fccc82d0a62a","entry":"stack_tokens_from_all_chunks","repo":"mim-solutions/bert_for_longer_texts","repo_kind":"listed","path":"belt_nlp/splitting.py","file_url":"https://github.com/mim-solutions/bert_for_longer_texts/blob/HEAD/belt_nlp/splitting.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"15b2fccc82d0a62a"}},{"code_sha256_prefix":"4123d6b63df245f2","entry":"tokenize_text_with_truncation","repo":"mim-solutions/bert_for_longer_texts","repo_kind":"listed","path":"belt_nlp/splitting.py","file_url":"https://github.com/mim-solutions/bert_for_longer_texts/blob/HEAD/belt_nlp/splitting.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":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"4123d6b63df245f2"}},{"code_sha256_prefix":"316d08e3b6936972","entry":"tokenize_whole_text","repo":"mim-solutions/bert_for_longer_texts","repo_kind":"listed","path":"belt_nlp/splitting.py","file_url":"https://github.com/mim-solutions/bert_for_longer_texts/blob/HEAD/belt_nlp/splitting.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"316d08e3b6936972"}},{"code_sha256_prefix":"41d96f44b38351ac","entry":"transform_list_of_texts","repo":"mim-solutions/bert_for_longer_texts","repo_kind":"listed","path":"belt_nlp/splitting.py","file_url":"https://github.com/mim-solutions/bert_for_longer_texts/blob/HEAD/belt_nlp/splitting.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"41d96f44b38351ac"}},{"code_sha256_prefix":"4d240665f4cb4490","entry":"transform_single_text","repo":"mim-solutions/bert_for_longer_texts","repo_kind":"listed","path":"belt_nlp/splitting.py","file_url":"https://github.com/mim-solutions/bert_for_longer_texts/blob/HEAD/belt_nlp/splitting.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"4d240665f4cb4490"}},{"code_sha256_prefix":"4603a2fe10eb193d","entry":"add_padding_tokens","repo":"mim-solutions/bert_for_longer_texts","repo_kind":"listed","path":"belt_nlp/splitting.py","file_url":"https://github.com/mim-solutions/bert_for_longer_texts/blob/HEAD/belt_nlp/splitting.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"4603a2fe10eb193d"}},{"code_sha256_prefix":"dd7b545b8b9f7fed","entry":"add_special_tokens_at_beginning_and_end","repo":"mim-solutions/bert_for_longer_texts","repo_kind":"listed","path":"belt_nlp/splitting.py","file_url":"https://github.com/mim-solutions/bert_for_longer_texts/blob/HEAD/belt_nlp/splitting.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"dd7b545b8b9f7fed"}},{"code_sha256_prefix":"0d09b5689924a10b","entry":"bigbird_block_sparse_attention","repo":"google-research/bigbird","repo_kind":"official","path":"bigbird/core/attention.py","file_url":"https://github.com/google-research/bigbird/blob/HEAD/bigbird/core/attention.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":"0d09b5689924a10b"}},{"code_sha256_prefix":"b18d818e15d8f5f2","entry":"bigbird_block_sparse_attention","repo":"monologg/kobigbird","repo_kind":"listed","path":"pretrain/kobigbird/attention.py","file_url":"https://github.com/monologg/kobigbird/blob/HEAD/pretrain/kobigbird/attention.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":"b18d818e15d8f5f2"}},{"code_sha256_prefix":"e219be299ea45b2d","entry":"check_split_parameters_consistency","repo":"mim-solutions/bert_for_longer_texts","repo_kind":"listed","path":"belt_nlp/splitting.py","file_url":"https://github.com/mim-solutions/bert_for_longer_texts/blob/HEAD/belt_nlp/splitting.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"e219be299ea45b2d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}