{"id":812,"slug":"joeliu996--naturebench","name":"NatureBench","author":"JoeLiu996","description":"\n\t\n\t\t\n\t\n\t\n\t\tDataset Card for NatureBench\n\t\n\n\n\nNatureBench is a cross-discipline benchmark of 27 tasks distilled from peer-reviewed Nature-family publications, spanning 6 scientific domains. It is designed to evaluate whether AI coding agents can move beyond reproduction toward discovery: each task asks an agent to solve a real scientific machine-learning problem and is scored against the source paper's reported state of the art.\n\n📄 arXiv paper: https://arxiv.org/abs/2606.24530\n💻 GitHub code… See the full description on the dataset page: https://huggingface.co/datasets/JoeLiu996/NatureBench.","tags":"[\"Language:en\",\"Size_categories:n<1K\",\"Format:json\",\"Modality:image\",\"Modality:text\",\"Library:datasets\"]","license":null,"framework":null,"parameters":null,"downloads":229551,"likes":0,"verified":0,"created_at":"2026-08-14 10:23:45","updated_at":"2026-08-14 10:23:45","source_url":"https://huggingface.co/datasets/JoeLiu996/NatureBench","source_platform":"huggingface","hf_repo_id":"JoeLiu996/NatureBench","ollama_name":"","category":"dataset","latest_version":"v1.0.0","version_count":1,"signature_count":1,"risk_level":null,"risk_score":null,"versions":[{"id":811,"model_id":812,"version":"v1.0.0","manifest_hash":"f48de6657b4986b44f1e2e8354de7939ab2b1bc6eaac806ff841fffc21ba9182","file_count":0,"total_size":0,"r2_manifest_key":"manifests/datasets/joeliu996--naturebench/v1.0.0.json","created_at":"2026-08-14 10:23:45"}],"files":[],"signatures":[{"id":1384,"version_id":811,"signer_did":"did:quantamrkt:registry:shield-v1","algorithm":"ML-DSA-65","signature_hex":"661c68c9599c9a9c9b85a4e71742ce41f34bae7cd57afc7b4775726732feaab3","attestation_type":"registry","signed_at":"2026-08-14 10:23:45"}],"hndl":null}