{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:APXA5ZUO3WNZ7BRBJIJ2PFX6CU","short_pith_number":"pith:APXA5ZUO","canonical_record":{"source":{"id":"2306.04362","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-07T11:52:36Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c152fa4152d6e7e219f49878e64e06dd43f51bfd4ef68e59c122048b913edb7d","abstract_canon_sha256":"c172e58923c5500b8c8c6dd16575a537011ce06bec8452385fc43cbd201e2ea5"},"schema_version":"1.0"},"canonical_sha256":"03ee0ee68edd9b9f86214a13a796fe151406ebf48858924bf149660c3ceb60d2","source":{"kind":"arxiv","id":"2306.04362","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.04362","created_at":"2026-07-05T06:18:28Z"},{"alias_kind":"arxiv_version","alias_value":"2306.04362v1","created_at":"2026-07-05T06:18:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04362","created_at":"2026-07-05T06:18:28Z"},{"alias_kind":"pith_short_12","alias_value":"APXA5ZUO3WNZ","created_at":"2026-07-05T06:18:28Z"},{"alias_kind":"pith_short_16","alias_value":"APXA5ZUO3WNZ7BRB","created_at":"2026-07-05T06:18:28Z"},{"alias_kind":"pith_short_8","alias_value":"APXA5ZUO","created_at":"2026-07-05T06:18:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:APXA5ZUO3WNZ7BRBJIJ2PFX6CU","target":"record","payload":{"canonical_record":{"source":{"id":"2306.04362","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-07T11:52:36Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c152fa4152d6e7e219f49878e64e06dd43f51bfd4ef68e59c122048b913edb7d","abstract_canon_sha256":"c172e58923c5500b8c8c6dd16575a537011ce06bec8452385fc43cbd201e2ea5"},"schema_version":"1.0"},"canonical_sha256":"03ee0ee68edd9b9f86214a13a796fe151406ebf48858924bf149660c3ceb60d2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:28.967888Z","signature_b64":"f7yCwC0v0G0nDP/+IyY+aXCMqYa+dIzizeYrAt4Zw+Ayu65MmksqnYnaGzcUNWmiFdAcBU0fqC1UXmnfOxvVBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03ee0ee68edd9b9f86214a13a796fe151406ebf48858924bf149660c3ceb60d2","last_reissued_at":"2026-07-05T06:18:28.967406Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:28.967406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.04362","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:18:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zpqzxv5dLVc9Ej0/ljapdBT0ihqnyhBNvMZzwKdgO/GsRoahWyIthQRgQUzpcGXELmuJQ0+Q0J8zmqN80QRJAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T20:52:26.212941Z"},"content_sha256":"c2079e0b130eae306062fc7d121ff20fa24ae2372fc58c0583979ae297644810","schema_version":"1.0","event_id":"sha256:c2079e0b130eae306062fc7d121ff20fa24ae2372fc58c0583979ae297644810"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:APXA5ZUO3WNZ7BRBJIJ2PFX6CU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Youku-mPLUG: A 10 Million Large-scale Chinese Video-Language Dataset for Pre-training and Benchmarks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Anwen Hu, Chenliang Li, Fei Huang, Guangwei Xu, Guohai Xu, Haiyang Xu, Jiabo Ye, Ji Zhang, Maofei Que, Ming Yan, Qinghao Ye, Qi Qian, Xiao Zeng, Xuan Wu, Yaya Shi, Yuan Miao","submitted_at":"2023-06-07T11:52:36Z","abstract_excerpt":"To promote the development of Vision-Language Pre-training (VLP) and multimodal Large Language Model (LLM) in the Chinese community, we firstly release the largest public Chinese high-quality video-language dataset named Youku-mPLUG, which is collected from Youku, a well-known Chinese video-sharing website, with strict criteria of safety, diversity, and quality. Youku-mPLUG contains 10 million Chinese video-text pairs filtered from 400 million raw videos across a wide range of 45 diverse categories for large-scale pre-training. In addition, to facilitate a comprehensive evaluation of video-lan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04362","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2306.04362/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:18:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"isE8U6c459/v0hrdHNcroTDpJjG38iHtU6C/jvaz0fA0RkRt7aKleImwbJ64kSnQj1l8t+30z2U68INLxOTbBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T20:52:26.213341Z"},"content_sha256":"baefa7a39e2bf09cce705f9895374b180199225ae4dd5f37b613caf34bcb6c2e","schema_version":"1.0","event_id":"sha256:baefa7a39e2bf09cce705f9895374b180199225ae4dd5f37b613caf34bcb6c2e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/APXA5ZUO3WNZ7BRBJIJ2PFX6CU/bundle.json","state_url":"https://pith.science/pith/APXA5ZUO3WNZ7BRBJIJ2PFX6CU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/APXA5ZUO3WNZ7BRBJIJ2PFX6CU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-11T20:52:26Z","links":{"resolver":"https://pith.science/pith/APXA5ZUO3WNZ7BRBJIJ2PFX6CU","bundle":"https://pith.science/pith/APXA5ZUO3WNZ7BRBJIJ2PFX6CU/bundle.json","state":"https://pith.science/pith/APXA5ZUO3WNZ7BRBJIJ2PFX6CU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/APXA5ZUO3WNZ7BRBJIJ2PFX6CU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:APXA5ZUO3WNZ7BRBJIJ2PFX6CU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c172e58923c5500b8c8c6dd16575a537011ce06bec8452385fc43cbd201e2ea5","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-07T11:52:36Z","title_canon_sha256":"c152fa4152d6e7e219f49878e64e06dd43f51bfd4ef68e59c122048b913edb7d"},"schema_version":"1.0","source":{"id":"2306.04362","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.04362","created_at":"2026-07-05T06:18:28Z"},{"alias_kind":"arxiv_version","alias_value":"2306.04362v1","created_at":"2026-07-05T06:18:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04362","created_at":"2026-07-05T06:18:28Z"},{"alias_kind":"pith_short_12","alias_value":"APXA5ZUO3WNZ","created_at":"2026-07-05T06:18:28Z"},{"alias_kind":"pith_short_16","alias_value":"APXA5ZUO3WNZ7BRB","created_at":"2026-07-05T06:18:28Z"},{"alias_kind":"pith_short_8","alias_value":"APXA5ZUO","created_at":"2026-07-05T06:18:28Z"}],"graph_snapshots":[{"event_id":"sha256:baefa7a39e2bf09cce705f9895374b180199225ae4dd5f37b613caf34bcb6c2e","target":"graph","created_at":"2026-07-05T06:18:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2306.04362/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To promote the development of Vision-Language Pre-training (VLP) and multimodal Large Language Model (LLM) in the Chinese community, we firstly release the largest public Chinese high-quality video-language dataset named Youku-mPLUG, which is collected from Youku, a well-known Chinese video-sharing website, with strict criteria of safety, diversity, and quality. Youku-mPLUG contains 10 million Chinese video-text pairs filtered from 400 million raw videos across a wide range of 45 diverse categories for large-scale pre-training. In addition, to facilitate a comprehensive evaluation of video-lan","authors_text":"Anwen Hu, Chenliang Li, Fei Huang, Guangwei Xu, Guohai Xu, Haiyang Xu, Jiabo Ye, Ji Zhang, Maofei Que, Ming Yan, Qinghao Ye, Qi Qian, Xiao Zeng, Xuan Wu, Yaya Shi, Yuan Miao","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-07T11:52:36Z","title":"Youku-mPLUG: A 10 Million Large-scale Chinese Video-Language Dataset for Pre-training and Benchmarks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04362","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c2079e0b130eae306062fc7d121ff20fa24ae2372fc58c0583979ae297644810","target":"record","created_at":"2026-07-05T06:18:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c172e58923c5500b8c8c6dd16575a537011ce06bec8452385fc43cbd201e2ea5","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-07T11:52:36Z","title_canon_sha256":"c152fa4152d6e7e219f49878e64e06dd43f51bfd4ef68e59c122048b913edb7d"},"schema_version":"1.0","source":{"id":"2306.04362","kind":"arxiv","version":1}},"canonical_sha256":"03ee0ee68edd9b9f86214a13a796fe151406ebf48858924bf149660c3ceb60d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03ee0ee68edd9b9f86214a13a796fe151406ebf48858924bf149660c3ceb60d2","first_computed_at":"2026-07-05T06:18:28.967406Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:18:28.967406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f7yCwC0v0G0nDP/+IyY+aXCMqYa+dIzizeYrAt4Zw+Ayu65MmksqnYnaGzcUNWmiFdAcBU0fqC1UXmnfOxvVBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:18:28.967888Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.04362","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2079e0b130eae306062fc7d121ff20fa24ae2372fc58c0583979ae297644810","sha256:baefa7a39e2bf09cce705f9895374b180199225ae4dd5f37b613caf34bcb6c2e"],"state_sha256":"a629153a2c89e7415f6c7d4fc804419971666330b4ad5673094dd1b8d2971c1e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pJnYfjA091NyXrX3gyYepPdPfgG1z7gQzWs10K2QKhY81LBQSALYMAwiDZGNX42WbeOUWHaprweoDh4zyzz6Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T20:52:26.216271Z","bundle_sha256":"8eeede59ca2016fd2730d8c3a005b2def06e2ccce3099bfe1e9fd3e176759b0b"}}