{"url":"/task/binary-text-classification","name":"Binary text classification","slug":"binary-text-classification","description_markdown":null,"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":20,"papers_with_code":12,"benchmarks":7,"benchmark_tables_in_archive":7,"benchmark_tables_shown":7,"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":10,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/binary-text-classification-on-ghostbuster-all","slug":"binary-text-classification-on-ghostbuster-all","dataset":"Ghostbuster (All Domains)","dataset_url":"/dataset/ghostbuster","rows_in_archive":2,"metrics":["F1 score"],"first_row_in_archive_order":{"model":"GigaCheck (Mistral-7B)","paper_title":"GigaCheck: Detecting LLM-generated Content","paper_url":"/paper/gigacheck-detecting-llm-generated-content","paper_date":"2024-10-31","arxiv_id":"2410.23728","code_links":[],"syntology":null}},{"leaderboard":"/sota/binary-text-classification-on-mage-arbitrary","slug":"binary-text-classification-on-mage-arbitrary","dataset":"MAGE (Arbitrary-domains & Arbitrary-models)","dataset_url":"/dataset/mage","rows_in_archive":2,"metrics":["Average Recall"],"first_row_in_archive_order":{"model":"GigaCheck (Mistral-7B)","paper_title":"GigaCheck: Detecting LLM-generated Content","paper_url":"/paper/gigacheck-detecting-llm-generated-content","paper_date":"2024-10-31","arxiv_id":"2410.23728","code_links":[],"syntology":null}},{"leaderboard":"/sota/binary-text-classification-on-mixset-binary","slug":"binary-text-classification-on-mixset-binary","dataset":"MixSet (Binary)","dataset_url":"/dataset/mixset","rows_in_archive":2,"metrics":["F1 score"],"first_row_in_archive_order":{"model":"GigaCheck (Mistral-7B)","paper_title":"GigaCheck: Detecting LLM-generated Content","paper_url":"/paper/gigacheck-detecting-llm-generated-content","paper_date":"2024-10-31","arxiv_id":"2410.23728","code_links":[],"syntology":null}},{"leaderboard":"/sota/binary-text-classification-on-turingbench","slug":"binary-text-classification-on-turingbench","dataset":"TURINGBENCH (Turing Test, GPT-3)","dataset_url":"/dataset/turingbench","rows_in_archive":2,"metrics":["F1 score"],"first_row_in_archive_order":{"model":"GigaCheck (Mistral-7B)","paper_title":"GigaCheck: Detecting LLM-generated Content","paper_url":"/paper/gigacheck-detecting-llm-generated-content","paper_date":"2024-10-31","arxiv_id":"2410.23728","code_links":[],"syntology":null}},{"leaderboard":"/sota/binary-text-classification-on-turingbench-1","slug":"binary-text-classification-on-turingbench-1","dataset":"TURINGBENCH (Turing Test, FAIR_wmt20)","dataset_url":"/dataset/turingbench","rows_in_archive":2,"metrics":["F1 score"],"first_row_in_archive_order":{"model":"GigaCheck (Mistral-7B)","paper_title":"GigaCheck: Detecting LLM-generated Content","paper_url":"/paper/gigacheck-detecting-llm-generated-content","paper_date":"2024-10-31","arxiv_id":"2410.23728","code_links":[],"syntology":null}},{"leaderboard":"/sota/binary-text-classification-on-tweepfake","slug":"binary-text-classification-on-tweepfake","dataset":"TweepFake","dataset_url":"/dataset/tweepfake","rows_in_archive":2,"metrics":["F1 score","Accuracy (%)"],"first_row_in_archive_order":{"model":"GigaCheck (Mistral-7B)","paper_title":"GigaCheck: Detecting LLM-generated Content","paper_url":"/paper/gigacheck-detecting-llm-generated-content","paper_date":"2024-10-31","arxiv_id":"2410.23728","code_links":[],"syntology":null}},{"leaderboard":"/sota/binary-text-classification-on-echr-non","slug":"binary-text-classification-on-echr-non","dataset":"ECHR Non-Anonymized","dataset_url":"/dataset/echr","rows_in_archive":1,"metrics":["Macro F1"],"first_row_in_archive_order":{"model":"HIER-BERT","paper_title":"Neural Legal Judgment Prediction in English","paper_url":"/paper/neural-legal-judgment-prediction-in-english","paper_date":"2019-06-05","arxiv_id":"1906.02059","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/echr","name":"ECHR","full_name":"","num_papers_in_archive":47},{"url":"/dataset/turingbench","name":"TURINGBENCH","full_name":"","num_papers_in_archive":18},{"url":"/dataset/tweepfake","name":"TweepFake","full_name":"","num_papers_in_archive":16},{"url":"/dataset/ghostbuster","name":"Ghostbuster","full_name":"","num_papers_in_archive":13},{"url":"/dataset/outfox","name":"OUTFOX","full_name":"","num_papers_in_archive":13},{"url":"/dataset/mage","name":"MAGE","full_name":"","num_papers_in_archive":11},{"url":"/dataset/mixset","name":"MixSet","full_name":"Mixcase Dataset","num_papers_in_archive":4},{"url":"/dataset/daccord","name":"DACCORD","full_name":"","num_papers_in_archive":2},{"url":"/dataset/bfrd","name":"BFRD","full_name":"Bengali Fake Review Dataset","num_papers_in_archive":1},{"url":"/dataset/this-is-not-a-dataset","name":"This is not a Dataset","full_name":"This is not a Dataset: A Large Negation Benchmark to Challenge Large Language Models","num_papers_in_archive":1}],"subtasks":[{"url":"/task/detection-of-potentially-void-clauses","name":"Detection of potentially void clauses"}],"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":12,"of":12,"tagged_in_all":20,"items":[{"url":"/paper/turingbench-a-benchmark-environment-for","title":"TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation","date":"2021-09-27","arxiv_id":"2109.13296","repositories_listed":3,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/llm-as-a-coauthor-the-challenges-of-detecting","title":"LLM-as-a-Coauthor: Can Mixed Human-Written and Machine-Generated Text Be Detected?","date":"2024-01-11","arxiv_id":"2401.05952","repositories_listed":2,"syntology":{"n":16,"n_ran":6,"n_unverified":10,"n_pointer_only":16}},{"url":"/paper/daccord-un-jeu-de-donnees-pour-la-detection","title":"DACCORD : un jeu de données pour la Détection Automatique d'énonCés COntRaDictoires en français","date":"2023-06-08","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/ghostbuster-detecting-text-ghostwritten-by","title":"Ghostbuster: Detecting Text Ghostwritten by Large Language Models","date":"2023-05-24","arxiv_id":"2305.15047","repositories_listed":2,"syntology":null},{"url":"/paper/deepfake-text-detection-in-the-wild","title":"MAGE: Machine-generated Text Detection in the Wild","date":"2023-05-22","arxiv_id":"2305.13242","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/learning-representations-for-soft-skill","title":"Learning Representations for Soft Skill Matching","date":"2018-07-20","arxiv_id":"1807.07741","repositories_listed":2,"syntology":null},{"url":"/paper/expectation-backpropagation-parameter-free","title":"Expectation Backpropagation: Parameter-Free Training of Multilayer Neural Networks with Continuous or Discrete Weights","date":"2014-12-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/hoaxpedia-a-unified-wikipedia-hoax-articles","title":"Hoaxpedia: A Unified Wikipedia Hoax Articles Dataset","date":"2024-05-03","arxiv_id":"2405.02175","repositories_listed":1,"syntology":null},{"url":"/paper/identification-of-the-relevance-of-comments","title":"Identification of the Relevance of Comments in Codes Using Bag of Words and Transformer Based Models","date":"2023-08-11","arxiv_id":"2308.06144","repositories_listed":1,"syntology":null},{"url":"/paper/active-learning-for-bert-an-empirical-study","title":"Active Learning for BERT: An Empirical Study","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/tweepfake-about-detecting-deepfake-tweets","title":"TweepFake: about Detecting Deepfake Tweets","date":"2020-07-31","arxiv_id":"2008.00036","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-shallow-and-deep-learning","title":"Evaluating shallow and deep learning strategies for the 2018 n2c2 shared task on clinical text classification","date":"2019-09-12","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":3,"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"}}