{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:H23EINQWJFZAPFII6O6KMSIBXB","short_pith_number":"pith:H23EINQW","canonical_record":{"source":{"id":"2103.06561","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-11T09:39:49Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"2fc767aa1fb9d3b62c75102788107cb77770bab37b17ee0198846a17034215f0","abstract_canon_sha256":"79a6e9436bee19c2daf54df36564ecd43d58d7f6b7c169620a943276481ffa28"},"schema_version":"1.0"},"canonical_sha256":"3eb64436164972079508f3bca64901b84ce47cbe9a971cc90c1b22e4fc1e7ac0","source":{"kind":"arxiv","id":"2103.06561","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.06561","created_at":"2026-07-05T02:56:15Z"},{"alias_kind":"arxiv_version","alias_value":"2103.06561v6","created_at":"2026-07-05T02:56:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.06561","created_at":"2026-07-05T02:56:15Z"},{"alias_kind":"pith_short_12","alias_value":"H23EINQWJFZA","created_at":"2026-07-05T02:56:15Z"},{"alias_kind":"pith_short_16","alias_value":"H23EINQWJFZAPFII","created_at":"2026-07-05T02:56:15Z"},{"alias_kind":"pith_short_8","alias_value":"H23EINQW","created_at":"2026-07-05T02:56:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:H23EINQWJFZAPFII6O6KMSIBXB","target":"record","payload":{"canonical_record":{"source":{"id":"2103.06561","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-11T09:39:49Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"2fc767aa1fb9d3b62c75102788107cb77770bab37b17ee0198846a17034215f0","abstract_canon_sha256":"79a6e9436bee19c2daf54df36564ecd43d58d7f6b7c169620a943276481ffa28"},"schema_version":"1.0"},"canonical_sha256":"3eb64436164972079508f3bca64901b84ce47cbe9a971cc90c1b22e4fc1e7ac0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:56:15.193238Z","signature_b64":"y+9KBfs96ZvagSMG520BS9mrGTBmBPxiOHLdwDIeuy/SKOwdCxwgt3ObrnyChqqnujS9DXWvPVSWiTDQD8j8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3eb64436164972079508f3bca64901b84ce47cbe9a971cc90c1b22e4fc1e7ac0","last_reissued_at":"2026-07-05T02:56:15.192783Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:56:15.192783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.06561","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:56:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2Uprye1j+BPtqcNOGLYbO/2IG/tQV9qDNMNYkj/fJU0ay4XfAAojKqBKyN5ossTRpNvcK1pvJ2Lsl6ijm/BKDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:38:43.715356Z"},"content_sha256":"3dbd9d7786dc0aaeefb504f11517ee45a380acc836e7075f6f394651bcdd4f31","schema_version":"1.0","event_id":"sha256:3dbd9d7786dc0aaeefb504f11517ee45a380acc836e7075f6f394651bcdd4f31"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:H23EINQWJFZAPFII6O6KMSIBXB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CV","authors_text":"Anwen Hu, Baogui Xu, Chuhao Jin, Danyang Hou, Guangzhen Liu, Guoxing Yang, Haoyu Lu, Heng Zhang, Jingyuan Wen, Jinming Zhao, Ji-Rong Wen, Junyi Li, Liang Zhang, Manli Zhang, Peiyu Liu, Qin Jin, Ruichen Li, Ruihua Song, Shizhe Chen, Wanqing Cui, Wayne Xin Zhao, Weihao Zheng, Xin Hong, Yanyan Lan, Yida Zhao, Yingyan Li, Yizhao Gao, Yuchong Sun, Yueqian Yang, Yuqi Huo, Yuqing Song, Zheng Gong, Zhicheng Dou, Zhiwu Lu, Zongzheng Xi","submitted_at":"2021-03-11T09:39:49Z","abstract_excerpt":"Multi-modal pre-training models have been intensively explored to bridge vision and language in recent years. However, most of them explicitly model the cross-modal interaction between image-text pairs, by assuming that there exists strong semantic correlation between the text and image modalities. Since this strong assumption is often invalid in real-world scenarios, we choose to implicitly model the cross-modal correlation for large-scale multi-modal pre-training, which is the focus of the Chinese project `WenLan' led by our team. Specifically, with the weak correlation assumption over image"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.06561","kind":"arxiv","version":6},"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/2103.06561/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":"2026-07-05T02:56:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+1NiYk9rYBzFSEdFbJYaX48B0B8BEIFa2cd2CJKIhbjxQ5Uuluz72273AbdNIQn+jIe4+ygxp5V8GejehiaWAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:38:43.715741Z"},"content_sha256":"e14bbb127dcd228408eed3ae824188d7642734647edca8f4011652fa5987529d","schema_version":"1.0","event_id":"sha256:e14bbb127dcd228408eed3ae824188d7642734647edca8f4011652fa5987529d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H23EINQWJFZAPFII6O6KMSIBXB/bundle.json","state_url":"https://pith.science/pith/H23EINQWJFZAPFII6O6KMSIBXB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H23EINQWJFZAPFII6O6KMSIBXB/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":"2026-07-07T11:38:43Z","links":{"resolver":"https://pith.science/pith/H23EINQWJFZAPFII6O6KMSIBXB","bundle":"https://pith.science/pith/H23EINQWJFZAPFII6O6KMSIBXB/bundle.json","state":"https://pith.science/pith/H23EINQWJFZAPFII6O6KMSIBXB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H23EINQWJFZAPFII6O6KMSIBXB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:H23EINQWJFZAPFII6O6KMSIBXB","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":"79a6e9436bee19c2daf54df36564ecd43d58d7f6b7c169620a943276481ffa28","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-11T09:39:49Z","title_canon_sha256":"2fc767aa1fb9d3b62c75102788107cb77770bab37b17ee0198846a17034215f0"},"schema_version":"1.0","source":{"id":"2103.06561","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.06561","created_at":"2026-07-05T02:56:15Z"},{"alias_kind":"arxiv_version","alias_value":"2103.06561v6","created_at":"2026-07-05T02:56:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.06561","created_at":"2026-07-05T02:56:15Z"},{"alias_kind":"pith_short_12","alias_value":"H23EINQWJFZA","created_at":"2026-07-05T02:56:15Z"},{"alias_kind":"pith_short_16","alias_value":"H23EINQWJFZAPFII","created_at":"2026-07-05T02:56:15Z"},{"alias_kind":"pith_short_8","alias_value":"H23EINQW","created_at":"2026-07-05T02:56:15Z"}],"graph_snapshots":[{"event_id":"sha256:e14bbb127dcd228408eed3ae824188d7642734647edca8f4011652fa5987529d","target":"graph","created_at":"2026-07-05T02:56:15Z","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/2103.06561/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal pre-training models have been intensively explored to bridge vision and language in recent years. However, most of them explicitly model the cross-modal interaction between image-text pairs, by assuming that there exists strong semantic correlation between the text and image modalities. Since this strong assumption is often invalid in real-world scenarios, we choose to implicitly model the cross-modal correlation for large-scale multi-modal pre-training, which is the focus of the Chinese project `WenLan' led by our team. Specifically, with the weak correlation assumption over image","authors_text":"Anwen Hu, Baogui Xu, Chuhao Jin, Danyang Hou, Guangzhen Liu, Guoxing Yang, Haoyu Lu, Heng Zhang, Jingyuan Wen, Jinming Zhao, Ji-Rong Wen, Junyi Li, Liang Zhang, Manli Zhang, Peiyu Liu, Qin Jin, Ruichen Li, Ruihua Song, Shizhe Chen, Wanqing Cui, Wayne Xin Zhao, Weihao Zheng, Xin Hong, Yanyan Lan, Yida Zhao, Yingyan Li, Yizhao Gao, Yuchong Sun, Yueqian Yang, Yuqi Huo, Yuqing Song, Zheng Gong, Zhicheng Dou, Zhiwu Lu, Zongzheng Xi","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-11T09:39:49Z","title":"WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.06561","kind":"arxiv","version":6},"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":"sha256:3dbd9d7786dc0aaeefb504f11517ee45a380acc836e7075f6f394651bcdd4f31","target":"record","created_at":"2026-07-05T02:56:15Z","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":"79a6e9436bee19c2daf54df36564ecd43d58d7f6b7c169620a943276481ffa28","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-11T09:39:49Z","title_canon_sha256":"2fc767aa1fb9d3b62c75102788107cb77770bab37b17ee0198846a17034215f0"},"schema_version":"1.0","source":{"id":"2103.06561","kind":"arxiv","version":6}},"canonical_sha256":"3eb64436164972079508f3bca64901b84ce47cbe9a971cc90c1b22e4fc1e7ac0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3eb64436164972079508f3bca64901b84ce47cbe9a971cc90c1b22e4fc1e7ac0","first_computed_at":"2026-07-05T02:56:15.192783Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:56:15.192783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y+9KBfs96ZvagSMG520BS9mrGTBmBPxiOHLdwDIeuy/SKOwdCxwgt3ObrnyChqqnujS9DXWvPVSWiTDQD8j8CA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:56:15.193238Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.06561","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3dbd9d7786dc0aaeefb504f11517ee45a380acc836e7075f6f394651bcdd4f31","sha256:e14bbb127dcd228408eed3ae824188d7642734647edca8f4011652fa5987529d"],"state_sha256":"f8f4191eba6868fe82f8d879d26f3315a0f08963e1d5c0a54da6c0e10a7c0de5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PAhs260PMRnm2OrsYWbRtETkhkBl1DVZcJiiStutrkrFK7GLqySFX8RO7I8BQbaiULOXN+Mx9ZCPx5wUX+Q+Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:38:43.717846Z","bundle_sha256":"07e3c49c12fc9dcdd3743aad1371d3695e5e7b80f29580c5ad96754091879fdf"}}