{"url":"/dataset/mt40k","name":"MT40K","full_name":null,"description_markdown":"The **MT40K** dataset for predicting malware threat intelligence is a collection of 40,000 triples generated from 27,354 unique entities and 34 relations. The corpus consists of approximately 1,100 de-identified plain text threat reports written between 2006-2021 and all CVE vulnerability descriptions created between 1990 to 2021. The annotated keyphrases were classified into entities derived from semantic categories defined in malware threat ontologies.","description_withheld":null,"homepage":"https://github.com/malkg-researcher/MalKG","introduced_date":"2021-02-10","introduced_date_note":null,"introduced_by":{"paper":"/paper/information-prediction-using-knowledge-graphs","title":"TINKER: A framework for Open source Cyberthreat Intelligence","first_author":"Nidhi Rastogi","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["MT40K"],"data_loaders":[{"repo":"https://github.com/liujie40/malkg-1","url":"https://github.com/liujie40/malkg-1","frameworks":["pytorch"]}],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+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."}