{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YM7GUUZLDVPH4P7S4WGMUXV2KZ","short_pith_number":"pith:YM7GUUZL","schema_version":"1.0","canonical_sha256":"c33e6a532b1d5e7e3ff2e58cca5eba566b4ecfd6fc7679bbcbe7cbf4adef8776","source":{"kind":"arxiv","id":"2202.06767","version":4},"attestation_state":"computed","paper":{"title":"Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chunjing Xu, Guansong Lu, Hang Xu, Jiaxi Gu, Lewei Yao, Lu Hou, Minzhe Niu, Runhui Huang, Wei Zhang, Xiaodan Liang, Xiaojun Meng, Xin Jiang","submitted_at":"2022-02-14T14:37:15Z","abstract_excerpt":"Vision-Language Pre-training (VLP) models have shown remarkable performance on various downstream tasks. Their success heavily relies on the scale of pre-trained cross-modal datasets. However, the lack of large-scale datasets and benchmarks in Chinese hinders the development of Chinese VLP models and broader multilingual applications. In this work, we release a large-scale Chinese cross-modal dataset named Wukong, which contains 100 million Chinese image-text pairs collected from the web. Wukong aims to benchmark different multi-modal pre-training methods to facilitate the VLP research and com"},"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":"2202.06767","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-14T14:37:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0beb470ada2fbefda337037fdcf9015a20450001f3a0704b51a8a121f690c0aa","abstract_canon_sha256":"f0fb6b82b7e2d2471e4e200db019d67c2f57cba6b1ce59b9a5de5392a5e7fe82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:01:50.749666Z","signature_b64":"9eo9ktfGy7Q7q2l+0ubxAqD+TEXtypY3rlGKIXa8bvBxxeFYmi0CmII4MoS1EZFPapNF043/7fRXwh72VFR+Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c33e6a532b1d5e7e3ff2e58cca5eba566b4ecfd6fc7679bbcbe7cbf4adef8776","last_reissued_at":"2026-07-05T05:01:50.749204Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:01:50.749204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chunjing Xu, Guansong Lu, Hang Xu, Jiaxi Gu, Lewei Yao, Lu Hou, Minzhe Niu, Runhui Huang, Wei Zhang, Xiaodan Liang, Xiaojun Meng, Xin Jiang","submitted_at":"2022-02-14T14:37:15Z","abstract_excerpt":"Vision-Language Pre-training (VLP) models have shown remarkable performance on various downstream tasks. Their success heavily relies on the scale of pre-trained cross-modal datasets. However, the lack of large-scale datasets and benchmarks in Chinese hinders the development of Chinese VLP models and broader multilingual applications. In this work, we release a large-scale Chinese cross-modal dataset named Wukong, which contains 100 million Chinese image-text pairs collected from the web. Wukong aims to benchmark different multi-modal pre-training methods to facilitate the VLP research and com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.06767","kind":"arxiv","version":4},"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/2202.06767/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":"2202.06767","created_at":"2026-07-05T05:01:50.749263+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.06767v4","created_at":"2026-07-05T05:01:50.749263+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.06767","created_at":"2026-07-05T05:01:50.749263+00:00"},{"alias_kind":"pith_short_12","alias_value":"YM7GUUZLDVPH","created_at":"2026-07-05T05:01:50.749263+00:00"},{"alias_kind":"pith_short_16","alias_value":"YM7GUUZLDVPH4P7S","created_at":"2026-07-05T05:01:50.749263+00:00"},{"alias_kind":"pith_short_8","alias_value":"YM7GUUZL","created_at":"2026-07-05T05:01:50.749263+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.00992","citing_title":"UniGlyph: Unified Segmentation-Conditioned Diffusion for Precise Visual Text Synthesis","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YM7GUUZLDVPH4P7S4WGMUXV2KZ","json":"https://pith.science/pith/YM7GUUZLDVPH4P7S4WGMUXV2KZ.json","graph_json":"https://pith.science/api/pith-number/YM7GUUZLDVPH4P7S4WGMUXV2KZ/graph.json","events_json":"https://pith.science/api/pith-number/YM7GUUZLDVPH4P7S4WGMUXV2KZ/events.json","paper":"https://pith.science/paper/YM7GUUZL"},"agent_actions":{"view_html":"https://pith.science/pith/YM7GUUZLDVPH4P7S4WGMUXV2KZ","download_json":"https://pith.science/pith/YM7GUUZLDVPH4P7S4WGMUXV2KZ.json","view_paper":"https://pith.science/paper/YM7GUUZL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.06767&json=true","fetch_graph":"https://pith.science/api/pith-number/YM7GUUZLDVPH4P7S4WGMUXV2KZ/graph.json","fetch_events":"https://pith.science/api/pith-number/YM7GUUZLDVPH4P7S4WGMUXV2KZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YM7GUUZLDVPH4P7S4WGMUXV2KZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YM7GUUZLDVPH4P7S4WGMUXV2KZ/action/storage_attestation","attest_author":"https://pith.science/pith/YM7GUUZLDVPH4P7S4WGMUXV2KZ/action/author_attestation","sign_citation":"https://pith.science/pith/YM7GUUZLDVPH4P7S4WGMUXV2KZ/action/citation_signature","submit_replication":"https://pith.science/pith/YM7GUUZLDVPH4P7S4WGMUXV2KZ/action/replication_record"}},"created_at":"2026-07-05T05:01:50.749263+00:00","updated_at":"2026-07-05T05:01:50.749263+00:00"}