{"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":"/method/cubert","slug":"cubert","name":"CuBERT","full_name":"CuBERT","full_name_withheld":false,"description_markdown":"**CuBERT**, or **Code Understanding BERT**, is a [BERT](https://paperswithcode.com/method/bert) based model for code understanding. In order to achieve this, the authors curate a massive corpus of Python programs collected from GitHub. GitHub projects are known to contain a large amount of duplicate code. To avoid biasing the model to such duplicated code, authors perform deduplication using the method of [Allamanis (2018)](https://arxiv.org/abs/1812.06469). The resulting corpus has 7.4 million files with a total of 9.3 billion tokens (16 million unique).","description_state":"present","introduced_year":null,"introduced_by":{"title":"Learning and Evaluating Contextual Embedding of Source Code","paper":"/paper/pre-trained-contextual-embedding-of-source-1","first_author":"Aditya Kanade","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/pre-trained-contextual-embedding-of-source-1"},"source":{"url":"https://arxiv.org/abs/2001.00059v3","title":"Learning and Evaluating Contextual Embedding of Source Code","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Code Generation Transformers","url":"/methods/category/code-generation-transformers","pwc_aliases":[]},{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Autoencoding Transformers","url":"/methods/category/autoencoding-transformers","pwc_aliases":[]},{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Language Models","url":"/methods/category/language-models","pwc_aliases":[]}],"n_papers_tagged":3,"archive_num_papers":3,"papers_newest_first":[{"paper":null,"slug":"intraoperative-perfusion-assessment-by","title":"Intraoperative perfusion assessment by continuous, low-latency hyperspectral light-field imaging: development, methodology, and clinical application","date":"2025-04-15","arxiv_id":"2504.10953","n_code_links":0,"syntology":null},{"paper":null,"slug":"clsebert-contrastive-learning-for-syntax","title":"SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation","date":"2021-08-10","arxiv_id":"2108.04556","n_code_links":0,"syntology":null},{"paper":"/paper/pre-trained-contextual-embedding-of-source-1","slug":"pre-trained-contextual-embedding-of-source-1","title":"Learning and Evaluating Contextual Embedding of Source Code","date":"2019-12-21","arxiv_id":"2001.00059","n_code_links":2,"syntology":null}],"papers_shown":3,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":3,"with_a_code_link":1,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":3,"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 the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"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 isolate this method inside it.","pages":[],"tasks":[{"task":"/task/clone-detection","name":"Clone Detection","papers":1},{"task":"/task/code-search","name":"Code Search","papers":1},{"task":"/task/code-translation","name":"Code Translation","papers":1},{"task":"/task/contextual-embedding-for-source-code","name":"Contextual Embedding for Source Code","papers":1},{"task":"/task/contrastive-learning","name":"Contrastive Learning","papers":1},{"task":"/task/exception-type","name":"Exception type","papers":1},{"task":"/task/function-docstring-mismatch","name":"Function-docstring mismatch","papers":1},{"task":"/task/language-modelling","name":"Language Modelling","papers":1},{"task":"/task/natural-language-understanding","name":"Natural Language Understanding","papers":1},{"task":"/task/program-repair","name":"Program Repair","papers":1},{"task":"/task/representation-learning","name":"Representation Learning","papers":1},{"task":"/task/swapped-operands","name":"Swapped operands","papers":1},{"task":"/task/type-prediction","name":"Type prediction","papers":1},{"task":"/task/variable-misuse","name":"Variable misuse","papers":1},{"task":"/task/wrong-binary-operator","name":"Wrong binary operator","papers":1}],"tasks_shown":15,"n_tasks":15,"usage_by_year":[{"year":"2019","papers":1},{"year":"2021","papers":1},{"year":"2025","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/cubert"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=CuBERT","read_at":"2026-10-05T00:54:21+00:00","query":"CuBERT","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"2001.00059","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'CuBERT' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":[],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"adb312e94243a925ff2e858300016389ba22d9380e4098bc01ab7c0066d9682c","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}