{"url":"/dataset/pubmed-abstracts","name":"PubMed Cognitive Control Abstracts","full_name":"CogText","description_markdown":"A collection of 385,705 scientific abstracts about Cognitive Control and their GPT-3 embeddings.","description_withheld":null,"homepage":"https://huggingface.co/datasets/morteza/cogtext","introduced_date":"2022-03-16","introduced_date_note":null,"introduced_by":{"paper":"/paper/linking-theories-and-methods-in-cognitive","title":"Linking Theories and Methods in Cognitive Sciences via Joint Embedding of the Scientific Literature: The Example of Cognitive Control","first_author":"Morteza Ansarinia","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"text similarity","url":"/task/text-similarity","datasets_with_task":"/datasets/task/text-similarity"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":[],"data_loaders":[],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/language-modelling-on-pubmed-abstracts","task":"Language Modelling","dataset_variant":"PubMed Cognitive Control Abstracts","rows":1,"metrics":["BPB"],"first_row_in_archive_order":{"model":"Gopher","paper":"/paper/scaling-language-models-methods-analysis-1","metrics":{"BPB":"0.577"},"code_links":[{"title":"allenai/dolma","url":"https://github.com/allenai/dolma"},{"title":"rvlopes/gloria","url":"https://github.com/rvlopes/gloria"},{"title":"bramiozo/PubScience","url":"https://github.com/bramiozo/PubScience"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/scaling-language-models-methods-analysis-1","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","date":"2021-12-08","rows_on_this_dataset":1,"code_links":3,"syntology":null}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"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."}