{"url":"/dataset/med","name":"MED","full_name":"Monotonicity Entailment Dataset","description_markdown":"**MED** is a new evaluation dataset that covers a wide range of monotonicity reasoning that was created by crowdsourcing and collected from linguistics publications. The dataset was constructed by collecting naturally-occurring examples by crowdsourcing and well-designed ones from linguistics publications.\r\nIt consists of 5,382 examples.\r\n\r\nSource: [https://github.com/verypluming/MED](https://github.com/verypluming/MED)\r\nImage Source: [https://www.aclweb.org/anthology/W19-4804v2.pdf](https://www.aclweb.org/anthology/W19-4804v2.pdf)","description_withheld":null,"homepage":"https://github.com/verypluming/MED","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/can-neural-networks-understand-monotonicity","title":"Can neural networks understand monotonicity reasoning?","first_author":"Hitomi Yanaka","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Natural Language Inference","url":"/task/natural-language-inference","datasets_with_task":"/datasets/task/natural-language-inference"},{"name":"Automated Theorem Proving","url":"/task/automated-theorem-proving","datasets_with_task":"/datasets/task/automated-theorem-proving"},{"name":"Data Augmentation","url":"/task/data-augmentation","datasets_with_task":"/datasets/task/data-augmentation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["MED"],"data_loaders":[{"repo":"https://github.com/verypluming/MED","url":"https://github.com/verypluming/MED","frameworks":[]}],"num_papers_in_archive":18,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/natural-language-inference-on-med","task":"Natural Language Inference","dataset_variant":"MED","rows":1,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"NeuralLog","paper":"/paper/neurallog-natural-language-inference-with","metrics":{"1:1 Accuracy":"0.934"},"code_links":[{"title":"eric11eca/NeuralLog","url":"https://github.com/eric11eca/NeuralLog"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/neurallog-natural-language-inference-with","title":"NeuralLog: Natural Language Inference with Joint Neural and Logical Reasoning","date":"2021-05-29","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}