{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JVKKDZ6GWWMWQA4Q6ZE2QHGVVR","short_pith_number":"pith:JVKKDZ6G","schema_version":"1.0","canonical_sha256":"4d54a1e7c6b599680390f649a81cd5ac785bb0f81f8762b30faee37871b80842","source":{"kind":"arxiv","id":"2306.07096","version":2},"attestation_state":"computed","paper":{"title":"Global and Local Semantic Completion Learning for Vision-Language Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengfei Cai, Hongfa Wang, Jie Jiang, Rong-Cheng Tu, Weijie Kong, Wei Liu, Wenzhe Zhao, Yatai Ji, Yujiu Yang","submitted_at":"2023-06-12T13:20:29Z","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"},"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":"2306.07096","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-12T13:20:29Z","cross_cats_sorted":[],"title_canon_sha256":"a23e63cd992ffeeb89dd5e4cf42472ad2bfa187edf58c559754f944d94b102b4","abstract_canon_sha256":"0d45a7ca6fc204e351bd86945e4cab88076f92c457e26c220c047657dc70e913"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:20:52.016900Z","signature_b64":"8OEAclpDJ9RK7WTvzF92GTbOoD4Cj01mUoZvXS+Q8WfEyKWfkgV60G0aKaN+m2b8wzvM618WW1ofMJz7AFT3Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d54a1e7c6b599680390f649a81cd5ac785bb0f81f8762b30faee37871b80842","last_reissued_at":"2026-07-05T07:20:52.016301Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:20:52.016301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Global and Local Semantic Completion Learning for Vision-Language Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengfei Cai, Hongfa Wang, Jie Jiang, Rong-Cheng Tu, Weijie Kong, Wei Liu, Wenzhe Zhao, Yatai Ji, Yujiu Yang","submitted_at":"2023-06-12T13:20:29Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07096","kind":"arxiv","version":2},"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/2306.07096/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":"2306.07096","created_at":"2026-07-05T07:20:52.016371+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.07096v2","created_at":"2026-07-05T07:20:52.016371+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07096","created_at":"2026-07-05T07:20:52.016371+00:00"},{"alias_kind":"pith_short_12","alias_value":"JVKKDZ6GWWMW","created_at":"2026-07-05T07:20:52.016371+00:00"},{"alias_kind":"pith_short_16","alias_value":"JVKKDZ6GWWMWQA4Q","created_at":"2026-07-05T07:20:52.016371+00:00"},{"alias_kind":"pith_short_8","alias_value":"JVKKDZ6G","created_at":"2026-07-05T07:20:52.016371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19952","citing_title":"Multimodal Reasoning Agent for Zero-Shot Composed Image Retrieval","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JVKKDZ6GWWMWQA4Q6ZE2QHGVVR","json":"https://pith.science/pith/JVKKDZ6GWWMWQA4Q6ZE2QHGVVR.json","graph_json":"https://pith.science/api/pith-number/JVKKDZ6GWWMWQA4Q6ZE2QHGVVR/graph.json","events_json":"https://pith.science/api/pith-number/JVKKDZ6GWWMWQA4Q6ZE2QHGVVR/events.json","paper":"https://pith.science/paper/JVKKDZ6G"},"agent_actions":{"view_html":"https://pith.science/pith/JVKKDZ6GWWMWQA4Q6ZE2QHGVVR","download_json":"https://pith.science/pith/JVKKDZ6GWWMWQA4Q6ZE2QHGVVR.json","view_paper":"https://pith.science/paper/JVKKDZ6G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.07096&json=true","fetch_graph":"https://pith.science/api/pith-number/JVKKDZ6GWWMWQA4Q6ZE2QHGVVR/graph.json","fetch_events":"https://pith.science/api/pith-number/JVKKDZ6GWWMWQA4Q6ZE2QHGVVR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JVKKDZ6GWWMWQA4Q6ZE2QHGVVR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JVKKDZ6GWWMWQA4Q6ZE2QHGVVR/action/storage_attestation","attest_author":"https://pith.science/pith/JVKKDZ6GWWMWQA4Q6ZE2QHGVVR/action/author_attestation","sign_citation":"https://pith.science/pith/JVKKDZ6GWWMWQA4Q6ZE2QHGVVR/action/citation_signature","submit_replication":"https://pith.science/pith/JVKKDZ6GWWMWQA4Q6ZE2QHGVVR/action/replication_record"}},"created_at":"2026-07-05T07:20:52.016371+00:00","updated_at":"2026-07-05T07:20:52.016371+00:00"}