{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:YM7GUUZLDVPH4P7S4WGMUXV2KZ","short_pith_number":"pith:YM7GUUZL","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"},"canonical_sha256":"c33e6a532b1d5e7e3ff2e58cca5eba566b4ecfd6fc7679bbcbe7cbf4adef8776","source":{"kind":"arxiv","id":"2202.06767","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.06767","created_at":"2026-07-05T05:01:50Z"},{"alias_kind":"arxiv_version","alias_value":"2202.06767v4","created_at":"2026-07-05T05:01:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.06767","created_at":"2026-07-05T05:01:50Z"},{"alias_kind":"pith_short_12","alias_value":"YM7GUUZLDVPH","created_at":"2026-07-05T05:01:50Z"},{"alias_kind":"pith_short_16","alias_value":"YM7GUUZLDVPH4P7S","created_at":"2026-07-05T05:01:50Z"},{"alias_kind":"pith_short_8","alias_value":"YM7GUUZL","created_at":"2026-07-05T05:01:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:YM7GUUZLDVPH4P7S4WGMUXV2KZ","target":"record","payload":{"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"},"canonical_sha256":"c33e6a532b1d5e7e3ff2e58cca5eba566b4ecfd6fc7679bbcbe7cbf4adef8776","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"},"source_kind":"arxiv","source_id":"2202.06767","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:01:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9++wzNiBvJKlsecS5r54ghr808OEP7/a5V/USQ9yEkRu6NsTDKZI8M/V6hA+Qk9GDR5N5EA/JQcDX0npuZc1Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:55:34.942924Z"},"content_sha256":"9ca4ca7d038db3619e27eee7d131b592b5a6d9ce3e3fe536d842382627a86f54","schema_version":"1.0","event_id":"sha256:9ca4ca7d038db3619e27eee7d131b592b5a6d9ce3e3fe536d842382627a86f54"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:YM7GUUZLDVPH4P7S4WGMUXV2KZ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:01:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XlvdWpkxEjsO5+yEQwsCnJ9aKxTSSjYTnCQ1stPACva/gFyiOKDvpm2Wrxlk1aq6p60KmJB17BmQySBqRjCtBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:55:34.943411Z"},"content_sha256":"8143cdfb5917bc84e5636d9da25363f2ac17c29a604f0154bf0ee1ba35d360d0","schema_version":"1.0","event_id":"sha256:8143cdfb5917bc84e5636d9da25363f2ac17c29a604f0154bf0ee1ba35d360d0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YM7GUUZLDVPH4P7S4WGMUXV2KZ/bundle.json","state_url":"https://pith.science/pith/YM7GUUZLDVPH4P7S4WGMUXV2KZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YM7GUUZLDVPH4P7S4WGMUXV2KZ/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":"2026-08-08T12:55:34Z","links":{"resolver":"https://pith.science/pith/YM7GUUZLDVPH4P7S4WGMUXV2KZ","bundle":"https://pith.science/pith/YM7GUUZLDVPH4P7S4WGMUXV2KZ/bundle.json","state":"https://pith.science/pith/YM7GUUZLDVPH4P7S4WGMUXV2KZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YM7GUUZLDVPH4P7S4WGMUXV2KZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:YM7GUUZLDVPH4P7S4WGMUXV2KZ","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":"f0fb6b82b7e2d2471e4e200db019d67c2f57cba6b1ce59b9a5de5392a5e7fe82","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-14T14:37:15Z","title_canon_sha256":"0beb470ada2fbefda337037fdcf9015a20450001f3a0704b51a8a121f690c0aa"},"schema_version":"1.0","source":{"id":"2202.06767","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.06767","created_at":"2026-07-05T05:01:50Z"},{"alias_kind":"arxiv_version","alias_value":"2202.06767v4","created_at":"2026-07-05T05:01:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.06767","created_at":"2026-07-05T05:01:50Z"},{"alias_kind":"pith_short_12","alias_value":"YM7GUUZLDVPH","created_at":"2026-07-05T05:01:50Z"},{"alias_kind":"pith_short_16","alias_value":"YM7GUUZLDVPH4P7S","created_at":"2026-07-05T05:01:50Z"},{"alias_kind":"pith_short_8","alias_value":"YM7GUUZL","created_at":"2026-07-05T05:01:50Z"}],"graph_snapshots":[{"event_id":"sha256:8143cdfb5917bc84e5636d9da25363f2ac17c29a604f0154bf0ee1ba35d360d0","target":"graph","created_at":"2026-07-05T05:01:50Z","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/2202.06767/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-14T14:37:15Z","title":"Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.06767","kind":"arxiv","version":4},"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":"sha256:9ca4ca7d038db3619e27eee7d131b592b5a6d9ce3e3fe536d842382627a86f54","target":"record","created_at":"2026-07-05T05:01:50Z","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":"f0fb6b82b7e2d2471e4e200db019d67c2f57cba6b1ce59b9a5de5392a5e7fe82","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-14T14:37:15Z","title_canon_sha256":"0beb470ada2fbefda337037fdcf9015a20450001f3a0704b51a8a121f690c0aa"},"schema_version":"1.0","source":{"id":"2202.06767","kind":"arxiv","version":4}},"canonical_sha256":"c33e6a532b1d5e7e3ff2e58cca5eba566b4ecfd6fc7679bbcbe7cbf4adef8776","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c33e6a532b1d5e7e3ff2e58cca5eba566b4ecfd6fc7679bbcbe7cbf4adef8776","first_computed_at":"2026-07-05T05:01:50.749204Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:01:50.749204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9eo9ktfGy7Q7q2l+0ubxAqD+TEXtypY3rlGKIXa8bvBxxeFYmi0CmII4MoS1EZFPapNF043/7fRXwh72VFR+Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:01:50.749666Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.06767","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ca4ca7d038db3619e27eee7d131b592b5a6d9ce3e3fe536d842382627a86f54","sha256:8143cdfb5917bc84e5636d9da25363f2ac17c29a604f0154bf0ee1ba35d360d0"],"state_sha256":"3e49ba7f82faf5d79492e1f98841e5ad9062277ef4aca4e7a55c3ad9ace8d601"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e5e3xnp0DU3Yhoo9SBRYJSau24H5dsg/AOfT4wSgnipUTYbw/I7QfsHZXxovekN5ZaPZSIPYr0sGXj+Rx3PFAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:55:34.946817Z","bundle_sha256":"95b11a4763c3798a95348f379edd5c686e6872341b84d41d5dfed4d8133cb7e2"}}