{"url":"/task/scientific-results-extraction","name":"Scientific Results Extraction","slug":"scientific-results-extraction","description_markdown":"Scientific results extraction is the task of extracting relevant result information (e.g., in the case of Machine learning performance results: task, dataset, metric name, metric value) from the scientific literature.","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":5,"papers_with_code":5,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"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":4,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/scientific-results-extraction-on-nlp-tdms-exp","slug":"scientific-results-extraction-on-nlp-tdms-exp","dataset":"NLP-TDMS (Exp, arXiv only)","dataset_url":null,"rows_in_archive":2,"metrics":["Macro F1","Macro Precision","Macro Recall","Micro F1","Micro Precision","Micro Recall"],"first_row_in_archive_order":{"model":"AxCell","paper_title":"AxCell: Automatic Extraction of Results from Machine Learning Papers","paper_url":"/paper/axcell-automatic-extraction-of-results-from","paper_date":"2020-04-29","arxiv_id":"2004.14356","code_links":[{"title":"paperswithcode/axcell","url":"https://github.com/paperswithcode/axcell"}],"syntology":{"n":14,"n_ran":0,"n_unverified":14,"n_pointer_only":0}}},{"leaderboard":"/sota/scientific-results-extraction-on-pwc","slug":"scientific-results-extraction-on-pwc","dataset":"PWC Leaderboards (restricted)","dataset_url":"/dataset/pwc-leaderboards","rows_in_archive":1,"metrics":["Macro F1","Macro Precision","Macro Recall","Micro F1","Micro Precision","Micro Recall"],"first_row_in_archive_order":{"model":"AxCell","paper_title":"AxCell: Automatic Extraction of Results from Machine Learning Papers","paper_url":"/paper/axcell-automatic-extraction-of-results-from","paper_date":"2020-04-29","arxiv_id":"2004.14356","code_links":[{"title":"paperswithcode/axcell","url":"https://github.com/paperswithcode/axcell"}],"syntology":{"n":14,"n_ran":0,"n_unverified":14,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/pwc-leaderboards","name":"PWC Leaderboards","full_name":"Papers with Code Leaderboards","num_papers_in_archive":3},{"url":"/dataset/arxivpapers","name":"ArxivPapers","full_name":"","num_papers_in_archive":2},{"url":"/dataset/segmentedtables","name":"SegmentedTables","full_name":"","num_papers_in_archive":2},{"url":"/dataset/linkedresults","name":"LinkedResults","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/information-retrieval","name":"Information Retrieval"}],"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":5,"of":5,"tagged_in_all":5,"items":[{"url":"/paper/predicting-real-time-scientific-experiments","title":"Predicting Real-time Scientific Experiments Using Transformer models and Reinforcement Learning","date":"2022-04-25","arxiv_id":"2204.11718","repositories_listed":1,"syntology":null},{"url":"/paper/automated-mining-of-leaderboards-for","title":"Automated Mining of Leaderboards for Empirical AI Research","date":"2021-08-31","arxiv_id":"2109.13089","repositories_listed":1,"syntology":null},{"url":"/paper/axcell-automatic-extraction-of-results-from","title":"AxCell: Automatic Extraction of Results from Machine Learning Papers","date":"2020-04-29","arxiv_id":"2004.14356","repositories_listed":1,"syntology":{"n":14,"n_ran":0,"n_unverified":14,"n_pointer_only":0}},{"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/identification-of-tasks-datasets-evaluation","title":"Identification of Tasks, Datasets, Evaluation Metrics, and Numeric Scores for Scientific Leaderboards Construction","date":"2019-06-21","arxiv_id":"1906.09317","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}}],"syntology_records":2,"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"}}