{"url":"/task/scientific-concept-extraction","name":"Scientific Concept Extraction","slug":"scientific-concept-extraction","description_markdown":"Identification of scientific concepts in research articles.","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":2,"papers_with_code":2,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/scientific-concept-extraction-on-stm-corpus","slug":"scientific-concept-extraction-on-stm-corpus","dataset":"STM-corpus","dataset_url":null,"rows_in_archive":2,"metrics":["Exact Span F1"],"first_row_in_archive_order":{"model":"SciBERT (active learning)","paper_title":"Domain-independent Extraction of Scientific Concepts from Research Articles","paper_url":"/paper/domain-independent-extraction-of-scientific","paper_date":"2020-01-09","arxiv_id":"2001.03067","code_links":[{"title":"arthurbra/stm-corpus","url":"https://github.com/arthurbra/stm-corpus/blob/master/README.md"}],"syntology":null}}],"datasets":[{"url":"/dataset/unarxive","name":"unarXive","full_name":"","num_papers_in_archive":9},{"url":"/dataset/semeval-2021-task-11-nlpcontributiongraph","name":"SemEval-2021 Task-11","full_name":"","num_papers_in_archive":8},{"url":"/dataset/semopenalex","name":"SemOpenAlex","full_name":"","num_papers_in_archive":6}],"subtasks":[],"parent_tasks":[{"url":"/task/named-entity-recognition-ner","name":"Named Entity Recognition (NER)"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":2,"of":2,"tagged_in_all":2,"items":[{"url":"/paper/unarxive-a-large-scholarly-data-set-with","title":"unarXive: A Large Scholarly Data Set with Publications' Full-Text, Annotated In-Text Citations, and Links to Metadata","date":"2020-03-02","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/domain-independent-extraction-of-scientific","title":"Domain-independent Extraction of Scientific Concepts from Research Articles","date":"2020-01-09","arxiv_id":"2001.03067","repositories_listed":1,"syntology":null}],"syntology_records":0,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}