{"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"}