{"entities":[{"id":"wmdp-benchmark-paper-2024","name":"The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning (arXiv:2403.03218)","subtype":"Preprint","description":"Version 7 of 15 May 2024, as described on the arXiv abstract page. Dates from the arXiv abstract page: submitted 5 March 2024 (v1), last revised 15 May 2024 (v7).","sourceIds":["source-ab-wmdp-abs"]},{"id":"arxiv","name":"arXiv"},{"id":"bio-misuse-capability-evaluation","name":"Biological misuse capability evaluation"}],"claims":[{"id":"ab-ev-wmdp-benchmark-measures","statement":"The WMDP benchmark paper states that it publicly releases a dataset of 3,668 multiple-choice questions serving as a proxy measurement of hazardous knowledge in biosecurity, cybersecurity and chemical security, developed by a consortium of academics and technical consultants and filtered to remove sensitive information before release.","derivation":"explicit","resolution":"supported","editorialState":"seed","evidenceIds":["evidence-ab-ev-wmdp-benchmark-measures-1","evidence-ab-ev-wmdp-benchmark-measures-2"]}],"sources":[{"id":"source-ab-wmdp-abs","title":"arXiv abstract page for arXiv:2403.03218 (The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning)","authors":["arXiv (Cornell University)"],"publisher":"arXiv (Cornell University)","publicationDate":null,"version":"Retrieved for the candidate pack on 2026-10-28 (SHA-256 c826f5d118daa2d0d9fda28de81b4460006387671abeb09faf704befe21c1c3e). Abstract page as served on 2026-10-28, listing v1 of 5 March 2024 and v7 of 15 May 2024 (the current version). Only the abstract page was read; the paper's unlearning method is deliberately not recorded. Retrieved again at admission on 2026-10-30 (SHA-256 111ae33a8fe87cffd7c31c9ba63f30ff31cb893d6f1cb86cb94767084668b500). Its wording can change; earlier wording is not authenticated.","evidenceUrl":"https://arxiv.org/abs/2403.03218","language":"en"}],"evidence":[{"id":"evidence-ab-ev-wmdp-benchmark-measures-1","sourceRole":"primary","support":"supports","verification":"machine_checked","retrievalRoute":"direct"},{"id":"evidence-ab-ev-wmdp-benchmark-measures-2","support":"supports","verification":"machine_checked","retrievalRoute":"direct"}],"at":{"entities":[1253,1261,1266],"claims":[3366],"sources":[1092],"evidence":[4620,4621]},"version":"1lg47t7"}