{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HOL4RIPVLGRQAVGFIJLCBP6L6T","short_pith_number":"pith:HOL4RIPV","schema_version":"1.0","canonical_sha256":"3b97c8a1f559a30054c5425620bfcbf4df5155e3a6403569b224a82ba50d71a8","source":{"kind":"arxiv","id":"2203.11480","version":5},"attestation_state":"computed","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2203.11480","created_at":"2026-07-05T04:19:07.604307+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.11480v5","created_at":"2026-07-05T04:19:07.604307+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.11480","created_at":"2026-07-05T04:19:07.604307+00:00"},{"alias_kind":"pith_short_12","alias_value":"HOL4RIPVLGRQ","created_at":"2026-07-05T04:19:07.604307+00:00"},{"alias_kind":"pith_short_16","alias_value":"HOL4RIPVLGRQAVGF","created_at":"2026-07-05T04:19:07.604307+00:00"},{"alias_kind":"pith_short_8","alias_value":"HOL4RIPV","created_at":"2026-07-05T04:19:07.604307+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HOL4RIPVLGRQAVGFIJLCBP6L6T","json":"https://pith.science/pith/HOL4RIPVLGRQAVGFIJLCBP6L6T.json","graph_json":"https://pith.science/api/pith-number/HOL4RIPVLGRQAVGFIJLCBP6L6T/graph.json","events_json":"https://pith.science/api/pith-number/HOL4RIPVLGRQAVGFIJLCBP6L6T/events.json","paper":"https://pith.science/paper/HOL4RIPV"},"agent_actions":{"view_html":"https://pith.science/pith/HOL4RIPVLGRQAVGFIJLCBP6L6T","download_json":"https://pith.science/pith/HOL4RIPVLGRQAVGFIJLCBP6L6T.json","view_paper":"https://pith.science/paper/HOL4RIPV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.11480&json=true","fetch_graph":"https://pith.science/api/pith-number/HOL4RIPVLGRQAVGFIJLCBP6L6T/graph.json","fetch_events":"https://pith.science/api/pith-number/HOL4RIPVLGRQAVGFIJLCBP6L6T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HOL4RIPVLGRQAVGFIJLCBP6L6T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HOL4RIPVLGRQAVGFIJLCBP6L6T/action/storage_attestation","attest_author":"https://pith.science/pith/HOL4RIPVLGRQAVGFIJLCBP6L6T/action/author_attestation","sign_citation":"https://pith.science/pith/HOL4RIPVLGRQAVGFIJLCBP6L6T/action/citation_signature","submit_replication":"https://pith.science/pith/HOL4RIPVLGRQAVGFIJLCBP6L6T/action/replication_record"}},"created_at":"2026-07-05T04:19:07.604307+00:00","updated_at":"2026-07-05T04:19:07.604307+00:00"}