{"id":958,"slug":"m-a-p--pin-200m","name":"PIN-200M","author":"m-a-p","description":"\n\t\n\t\t\n\t\tPIN-200M\n\t\n\nA mini version of \"PIN: A Knowledge-Intensive Dataset for Paired and Interleaved Multimodal Documents\"\nPaper: https://arxiv.org/abs/2406.13923\nThis dataset contains around 200M samples in PIN format, with around 312 TB storage.\n🚀 News\n[ 2025.09.22 ] !NEW! 🔥 We have completed the final version of the PIN-200M dataset and conducted some simple statistics on it.\n[ 2024.12.06 ] !NEW! 🔥 We have updated the quality signals, enabling a swift assessment of whether a sample meets… See the full description on the dataset page: https://huggingface.co/datasets/m-a-p/PIN-200M.","tags":"[\"Language:en\",\"Language:zh\",\"Size_categories:10K<n<100K\",\"Format:json\",\"Modality:text\",\"Library:datasets\"]","license":null,"framework":null,"parameters":null,"downloads":217404,"likes":28,"verified":0,"created_at":"2026-10-04 14:23:29","updated_at":"2026-10-05 07:23:34","source_url":"https://huggingface.co/datasets/m-a-p/PIN-200M","source_platform":"huggingface","hf_repo_id":"m-a-p/PIN-200M","ollama_name":"","category":"dataset","latest_version":"v1.0.0","version_count":1,"signature_count":1,"risk_level":null,"risk_score":null,"versions":[{"id":957,"model_id":958,"version":"v1.0.0","manifest_hash":"7dd908d4884b64ef1592334b2dd59d82bc8aad838c7a8c987fa5b17b29c0cc09","file_count":0,"total_size":0,"r2_manifest_key":"manifests/datasets/m-a-p--pin-200m/v1.0.0.json","created_at":"2026-10-04 14:23:29"}],"files":[],"signatures":[{"id":1530,"version_id":957,"signer_did":"did:quantamrkt:registry:shield-v1","algorithm":"ML-DSA-65","signature_hex":"c06e15cc4f9f543dbce562174fcdf23ac5499487c0611383e0f34b5def497ba6","attestation_type":"registry","signed_at":"2026-10-04 14:23:29"}],"hndl":null}