{"url":"/task/label-error-detection","name":"Label Error Detection","slug":"label-error-detection","description_markdown":"Identify labeling errors in data","categories":[{"name":"Miscellaneous","url":"/area/miscellaneous"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":12,"papers_with_code":8,"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":0,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/label-error-detection-on-trec-6","slug":"label-error-detection-on-trec-6","dataset":"TREC-6","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"github.com/guotong1988/Automatic-Label-Error-Correction","paper_title":"The Re-Label Method For Data-Centric Machine Learning","paper_url":"/paper/the-re-label-method-for-data-centric-machine","paper_date":"2023-02-09","arxiv_id":"2302.04391","code_links":[{"title":"guotong1988/Automatic-Label-Error-Correction","url":"https://github.com/guotong1988/Automatic-Label-Error-Correction"}],"syntology":null}}],"datasets":[],"subtasks":[],"parent_tasks":[],"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":8,"of":8,"tagged_in_all":12,"items":[{"url":"/paper/identifying-incorrect-annotations-in-multi","title":"Identifying Incorrect Annotations in Multi-Label Classification Data","date":"2022-11-25","arxiv_id":"2211.13895","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/wenetspeech-a-10000-hours-multi-domain","title":"WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition","date":"2021-10-07","arxiv_id":"2110.03370","repositories_listed":2,"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/2505-11034","title":"CleanPatrick: A Benchmark for Image Data Cleaning","date":"2025-05-16","arxiv_id":"2505.11034","repositories_listed":1,"syntology":null},{"url":"/paper/aqua-a-benchmarking-tool-for-label-quality-1","title":"AQuA: A Benchmarking Tool for Label Quality Assessment","date":"2023-06-15","arxiv_id":"2306.09467","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/identifying-label-errors-in-object-detection","title":"Identifying Label Errors in Object Detection Datasets by Loss Inspection","date":"2023-03-13","arxiv_id":"2303.06999","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/the-re-label-method-for-data-centric-machine","title":"The Re-Label Method For Data-Centric Machine Learning","date":"2023-02-09","arxiv_id":"2302.04391","repositories_listed":1,"syntology":null},{"url":"/paper/ctrl-clustering-training-losses-for-label","title":"CTRL: Clustering Training Losses for Label Error Detection","date":"2022-08-17","arxiv_id":"2208.08464","repositories_listed":1,"syntology":null},{"url":"/paper/automated-detection-of-label-errors-in","title":"Automated Detection of Label Errors in Semantic Segmentation Datasets via Deep Learning and Uncertainty Quantification","date":"2022-07-13","arxiv_id":"2207.06104","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}}],"syntology_records":5,"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"}}