{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:HOL4RIPVLGRQAVGFIJLCBP6L6T","short_pith_number":"pith:HOL4RIPV","canonical_record":{"source":{"id":"2203.11480","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-22T06:12:20Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"5bf9149012de8314088ccc281e3017f8af5dc4cf96d394cc2281b7cee3b2788f","abstract_canon_sha256":"a87614ce07d71e9c033d4f48182d48da829029401b5c9883169424668686bbdd"},"schema_version":"1.0"},"canonical_sha256":"3b97c8a1f559a30054c5425620bfcbf4df5155e3a6403569b224a82ba50d71a8","source":{"kind":"arxiv","id":"2203.11480","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.11480","created_at":"2026-07-05T04:19:07Z"},{"alias_kind":"arxiv_version","alias_value":"2203.11480v5","created_at":"2026-07-05T04:19:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.11480","created_at":"2026-07-05T04:19:07Z"},{"alias_kind":"pith_short_12","alias_value":"HOL4RIPVLGRQ","created_at":"2026-07-05T04:19:07Z"},{"alias_kind":"pith_short_16","alias_value":"HOL4RIPVLGRQAVGF","created_at":"2026-07-05T04:19:07Z"},{"alias_kind":"pith_short_8","alias_value":"HOL4RIPV","created_at":"2026-07-05T04:19:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:HOL4RIPVLGRQAVGFIJLCBP6L6T","target":"record","payload":{"canonical_record":{"source":{"id":"2203.11480","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-22T06:12:20Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"5bf9149012de8314088ccc281e3017f8af5dc4cf96d394cc2281b7cee3b2788f","abstract_canon_sha256":"a87614ce07d71e9c033d4f48182d48da829029401b5c9883169424668686bbdd"},"schema_version":"1.0"},"canonical_sha256":"3b97c8a1f559a30054c5425620bfcbf4df5155e3a6403569b224a82ba50d71a8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:19:07.604647Z","signature_b64":"5ePSmxiylLSgmB1T8n7i/xuNpVeH93LFLAqH3tVa8xz5tfIFYZr456dDmyw2/DMkbmt6ew9FWTN4cUO5V2yOCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b97c8a1f559a30054c5425620bfcbf4df5155e3a6403569b224a82ba50d71a8","last_reissued_at":"2026-07-05T04:19:07.604252Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:19:07.604252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.11480","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:19:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h8r6Oko1Dp7BPcZo9NW1R6GJSrpFOY2LgLPSi8w6Z65FnwIiJfEoWyECehJ+FW6rRvIsuAakDOuGznIt2NhuCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:18:22.226938Z"},"content_sha256":"a701a9cfbc657ed256d4c26e30f2f520e413643e919a43acfc952e6b66a5c9ef","schema_version":"1.0","event_id":"sha256:a701a9cfbc657ed256d4c26e30f2f520e413643e919a43acfc952e6b66a5c9ef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:HOL4RIPVLGRQAVGFIJLCBP6L6T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WuDaoMM: A large-scale Multi-Modal Dataset for Pre-training models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Hanyu Zhao, Jiahong Leng, Jie Tang, Junyi Li, Peiyu Liu, Sha Yuan, Shuai Zhao, Wayne Xin Zhao, Zhao Xue, Zheng Gong","submitted_at":"2022-03-22T06:12:20Z","abstract_excerpt":"Compared with the domain-specific model, the vision-language pre-training models (VLPMs) have shown superior performance on downstream tasks with fast fine-tuning process. For example, ERNIE-ViL, Oscar and UNIMO trained VLPMs with a uniform transformers stack architecture and large amounts of image-text paired data, achieving remarkable results on downstream tasks such as image-text reference(IR and TR), vision question answering (VQA) and image captioning (IC) etc. During the training phase, VLPMs are always fed with a combination of multiple public datasets to meet the demand of large-scare "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.11480","kind":"arxiv","version":5},"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/2203.11480/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":"2026-07-05T04:19:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OoIgqkBt5FKKxxwm7eiRlz36M3gqNev36B3zbMbFe1yG/WPV06qLIzASbMme31uKcvSkca0KJZnzAvC5sHKTAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:18:22.227443Z"},"content_sha256":"3b7a9b5814106b0daa3e8dcafe5bae22127886c944c69f36f76890516582f08a","schema_version":"1.0","event_id":"sha256:3b7a9b5814106b0daa3e8dcafe5bae22127886c944c69f36f76890516582f08a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HOL4RIPVLGRQAVGFIJLCBP6L6T/bundle.json","state_url":"https://pith.science/pith/HOL4RIPVLGRQAVGFIJLCBP6L6T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HOL4RIPVLGRQAVGFIJLCBP6L6T/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":"2026-08-06T06:18:22Z","links":{"resolver":"https://pith.science/pith/HOL4RIPVLGRQAVGFIJLCBP6L6T","bundle":"https://pith.science/pith/HOL4RIPVLGRQAVGFIJLCBP6L6T/bundle.json","state":"https://pith.science/pith/HOL4RIPVLGRQAVGFIJLCBP6L6T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HOL4RIPVLGRQAVGFIJLCBP6L6T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:HOL4RIPVLGRQAVGFIJLCBP6L6T","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":"a87614ce07d71e9c033d4f48182d48da829029401b5c9883169424668686bbdd","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-22T06:12:20Z","title_canon_sha256":"5bf9149012de8314088ccc281e3017f8af5dc4cf96d394cc2281b7cee3b2788f"},"schema_version":"1.0","source":{"id":"2203.11480","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.11480","created_at":"2026-07-05T04:19:07Z"},{"alias_kind":"arxiv_version","alias_value":"2203.11480v5","created_at":"2026-07-05T04:19:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.11480","created_at":"2026-07-05T04:19:07Z"},{"alias_kind":"pith_short_12","alias_value":"HOL4RIPVLGRQ","created_at":"2026-07-05T04:19:07Z"},{"alias_kind":"pith_short_16","alias_value":"HOL4RIPVLGRQAVGF","created_at":"2026-07-05T04:19:07Z"},{"alias_kind":"pith_short_8","alias_value":"HOL4RIPV","created_at":"2026-07-05T04:19:07Z"}],"graph_snapshots":[{"event_id":"sha256:3b7a9b5814106b0daa3e8dcafe5bae22127886c944c69f36f76890516582f08a","target":"graph","created_at":"2026-07-05T04:19:07Z","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/2203.11480/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Compared with the domain-specific model, the vision-language pre-training models (VLPMs) have shown superior performance on downstream tasks with fast fine-tuning process. For example, ERNIE-ViL, Oscar and UNIMO trained VLPMs with a uniform transformers stack architecture and large amounts of image-text paired data, achieving remarkable results on downstream tasks such as image-text reference(IR and TR), vision question answering (VQA) and image captioning (IC) etc. During the training phase, VLPMs are always fed with a combination of multiple public datasets to meet the demand of large-scare ","authors_text":"Hanyu Zhao, Jiahong Leng, Jie Tang, Junyi Li, Peiyu Liu, Sha Yuan, Shuai Zhao, Wayne Xin Zhao, Zhao Xue, Zheng Gong","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-22T06:12:20Z","title":"WuDaoMM: A large-scale Multi-Modal Dataset for Pre-training models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.11480","kind":"arxiv","version":5},"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:a701a9cfbc657ed256d4c26e30f2f520e413643e919a43acfc952e6b66a5c9ef","target":"record","created_at":"2026-07-05T04:19:07Z","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":"a87614ce07d71e9c033d4f48182d48da829029401b5c9883169424668686bbdd","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-22T06:12:20Z","title_canon_sha256":"5bf9149012de8314088ccc281e3017f8af5dc4cf96d394cc2281b7cee3b2788f"},"schema_version":"1.0","source":{"id":"2203.11480","kind":"arxiv","version":5}},"canonical_sha256":"3b97c8a1f559a30054c5425620bfcbf4df5155e3a6403569b224a82ba50d71a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b97c8a1f559a30054c5425620bfcbf4df5155e3a6403569b224a82ba50d71a8","first_computed_at":"2026-07-05T04:19:07.604252Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:19:07.604252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5ePSmxiylLSgmB1T8n7i/xuNpVeH93LFLAqH3tVa8xz5tfIFYZr456dDmyw2/DMkbmt6ew9FWTN4cUO5V2yOCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:19:07.604647Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.11480","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a701a9cfbc657ed256d4c26e30f2f520e413643e919a43acfc952e6b66a5c9ef","sha256:3b7a9b5814106b0daa3e8dcafe5bae22127886c944c69f36f76890516582f08a"],"state_sha256":"6c2f23f7bce8f3b82729b0402acc15b742f74900648fe0f8f719fea1bd5452dd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WYq0CjLOYFifDyVx1ez7x3Z+7uv/MSieAVR7JyV04kntDECfKn67is7ixAHTel5ECkGXPCJHYnNtg9ez5XEGCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:18:22.230881Z","bundle_sha256":"4876cd1342752dc566a62a82d1e695dbf55b5d5becc667fa6ed7fadf7dc1502e"}}