{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JVKKDZ6GWWMWQA4Q6ZE2QHGVVR","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":"0d45a7ca6fc204e351bd86945e4cab88076f92c457e26c220c047657dc70e913","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-12T13:20:29Z","title_canon_sha256":"a23e63cd992ffeeb89dd5e4cf42472ad2bfa187edf58c559754f944d94b102b4"},"schema_version":"1.0","source":{"id":"2306.07096","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.07096","created_at":"2026-07-05T07:20:52Z"},{"alias_kind":"arxiv_version","alias_value":"2306.07096v2","created_at":"2026-07-05T07:20:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07096","created_at":"2026-07-05T07:20:52Z"},{"alias_kind":"pith_short_12","alias_value":"JVKKDZ6GWWMW","created_at":"2026-07-05T07:20:52Z"},{"alias_kind":"pith_short_16","alias_value":"JVKKDZ6GWWMWQA4Q","created_at":"2026-07-05T07:20:52Z"},{"alias_kind":"pith_short_8","alias_value":"JVKKDZ6G","created_at":"2026-07-05T07:20:52Z"}],"graph_snapshots":[{"event_id":"sha256:3cd8a0f0783c0269abdfb985c4ba557935438d220b402d19faa721a9c7d3a052","target":"graph","created_at":"2026-07-05T07:20:52Z","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/2306.07096/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cross-modal alignment plays a crucial role in vision-language pre-training (VLP) models, enabling them to capture meaningful associations across different modalities. For this purpose, numerous masked modeling tasks have been proposed for VLP to further promote cross-modal interactions. The core idea of previous masked modeling tasks is to focus on reconstructing the masked tokens based on visible context for learning local-local alignment. However, most of them pay little attention to the global semantic features generated for the masked data, resulting in a limited cross-modal alignment abil","authors_text":"Chengfei Cai, Hongfa Wang, Jie Jiang, Rong-Cheng Tu, Weijie Kong, Wei Liu, Wenzhe Zhao, Yatai Ji, Yujiu Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-12T13:20:29Z","title":"Global and Local Semantic Completion Learning for Vision-Language Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07096","kind":"arxiv","version":2},"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":"sha256:1637670e5000d946f6d8c49c4d6741f021d36ba98fd52e20e079a403f8635fa7","target":"record","created_at":"2026-07-05T07:20:52Z","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":"0d45a7ca6fc204e351bd86945e4cab88076f92c457e26c220c047657dc70e913","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-12T13:20:29Z","title_canon_sha256":"a23e63cd992ffeeb89dd5e4cf42472ad2bfa187edf58c559754f944d94b102b4"},"schema_version":"1.0","source":{"id":"2306.07096","kind":"arxiv","version":2}},"canonical_sha256":"4d54a1e7c6b599680390f649a81cd5ac785bb0f81f8762b30faee37871b80842","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d54a1e7c6b599680390f649a81cd5ac785bb0f81f8762b30faee37871b80842","first_computed_at":"2026-07-05T07:20:52.016301Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:20:52.016301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8OEAclpDJ9RK7WTvzF92GTbOoD4Cj01mUoZvXS+Q8WfEyKWfkgV60G0aKaN+m2b8wzvM618WW1ofMJz7AFT3Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:20:52.016900Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.07096","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1637670e5000d946f6d8c49c4d6741f021d36ba98fd52e20e079a403f8635fa7","sha256:3cd8a0f0783c0269abdfb985c4ba557935438d220b402d19faa721a9c7d3a052"],"state_sha256":"94a8dab497bbe7f31cba9a584dd456ef400accfb34e0196607073521bd56c4ac"}