{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LPYHI5BLKSH3IP6NT2HKU3JFRN","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":"066a08be9bbfc045a54cffd56f9bf5c06870013ab6094da2e46fd7cc172e4885","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-02-18T07:54:02Z","title_canon_sha256":"d0a7dd67196dc872d7c9349ebc4d0a603b505b489df291bae8dc01f9d29cde98"},"schema_version":"1.0","source":{"id":"2202.09061","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.09061","created_at":"2026-07-05T08:09:22Z"},{"alias_kind":"arxiv_version","alias_value":"2202.09061v4","created_at":"2026-07-05T08:09:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.09061","created_at":"2026-07-05T08:09:22Z"},{"alias_kind":"pith_short_12","alias_value":"LPYHI5BLKSH3","created_at":"2026-07-05T08:09:22Z"},{"alias_kind":"pith_short_16","alias_value":"LPYHI5BLKSH3IP6N","created_at":"2026-07-05T08:09:22Z"},{"alias_kind":"pith_short_8","alias_value":"LPYHI5BL","created_at":"2026-07-05T08:09:22Z"}],"graph_snapshots":[{"event_id":"sha256:ac63021d46ef8ec2bfef575754aceea18e1c8c735e2c9411088f93706a533be3","target":"graph","created_at":"2026-07-05T08:09:22Z","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/2202.09061/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the past few years, the emergence of pre-training models has brought uni-modal fields such as computer vision (CV) and natural language processing (NLP) to a new era. Substantial works have shown they are beneficial for downstream uni-modal tasks and avoid training a new model from scratch. So can such pre-trained models be applied to multi-modal tasks? Researchers have explored this problem and made significant progress. This paper surveys recent advances and new frontiers in vision-language pre-training (VLP), including image-text and video-text pre-training. To give readers a better over","authors_text":"Bo Xu, Duzhen Zhang, Feilong Chen, Jing Shi, Minglun Han, Shuang Xu, Xiuyi Chen","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-02-18T07:54:02Z","title":"VLP: A Survey on Vision-Language Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.09061","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":"sha256:30a68d80dcd7e2d75a52d4f1e5606bd6a72f533a1b3a2e9fe8206da3e7d865d5","target":"record","created_at":"2026-07-05T08:09:22Z","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":"066a08be9bbfc045a54cffd56f9bf5c06870013ab6094da2e46fd7cc172e4885","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-02-18T07:54:02Z","title_canon_sha256":"d0a7dd67196dc872d7c9349ebc4d0a603b505b489df291bae8dc01f9d29cde98"},"schema_version":"1.0","source":{"id":"2202.09061","kind":"arxiv","version":4}},"canonical_sha256":"5bf074742b548fb43fcd9e8eaa6d258b7a938edd89cbf9b82b74b7efbc6b5f64","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5bf074742b548fb43fcd9e8eaa6d258b7a938edd89cbf9b82b74b7efbc6b5f64","first_computed_at":"2026-07-05T08:09:22.161610Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:09:22.161610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dOQsHnptGI5x95XwT8fxpGPPJkXQ9VZyYa1FeAbM42F5vBz3WtL03jje5JAT69noG/K9GsH18odT91F1ICHQAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:09:22.161956Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.09061","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30a68d80dcd7e2d75a52d4f1e5606bd6a72f533a1b3a2e9fe8206da3e7d865d5","sha256:ac63021d46ef8ec2bfef575754aceea18e1c8c735e2c9411088f93706a533be3"],"state_sha256":"73af62eb36dc55303264911c1789aef5f19f470d7bf7b3ef250350ef31c979ff"}