{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LPYHI5BLKSH3IP6NT2HKU3JFRN","short_pith_number":"pith:LPYHI5BL","schema_version":"1.0","canonical_sha256":"5bf074742b548fb43fcd9e8eaa6d258b7a938edd89cbf9b82b74b7efbc6b5f64","source":{"kind":"arxiv","id":"2202.09061","version":4},"attestation_state":"computed","paper":{"title":"VLP: A Survey on Vision-Language Pre-training","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Bo Xu, Duzhen Zhang, Feilong Chen, Jing Shi, Minglun Han, Shuang Xu, Xiuyi Chen","submitted_at":"2022-02-18T07:54:02Z","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"},"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":"2202.09061","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-02-18T07:54:02Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d0a7dd67196dc872d7c9349ebc4d0a603b505b489df291bae8dc01f9d29cde98","abstract_canon_sha256":"066a08be9bbfc045a54cffd56f9bf5c06870013ab6094da2e46fd7cc172e4885"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:09:22.161956Z","signature_b64":"dOQsHnptGI5x95XwT8fxpGPPJkXQ9VZyYa1FeAbM42F5vBz3WtL03jje5JAT69noG/K9GsH18odT91F1ICHQAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bf074742b548fb43fcd9e8eaa6d258b7a938edd89cbf9b82b74b7efbc6b5f64","last_reissued_at":"2026-07-05T08:09:22.161610Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:09:22.161610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLP: A Survey on Vision-Language Pre-training","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Bo Xu, Duzhen Zhang, Feilong Chen, Jing Shi, Minglun Han, Shuang Xu, Xiuyi Chen","submitted_at":"2022-02-18T07:54:02Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.09061","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/2202.09061/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":"2202.09061","created_at":"2026-07-05T08:09:22.161664+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.09061v4","created_at":"2026-07-05T08:09:22.161664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.09061","created_at":"2026-07-05T08:09:22.161664+00:00"},{"alias_kind":"pith_short_12","alias_value":"LPYHI5BLKSH3","created_at":"2026-07-05T08:09:22.161664+00:00"},{"alias_kind":"pith_short_16","alias_value":"LPYHI5BLKSH3IP6N","created_at":"2026-07-05T08:09:22.161664+00:00"},{"alias_kind":"pith_short_8","alias_value":"LPYHI5BL","created_at":"2026-07-05T08:09:22.161664+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.06963","citing_title":"Learning in Deep Networks under Dale's Constraint","ref_index":141,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LPYHI5BLKSH3IP6NT2HKU3JFRN","json":"https://pith.science/pith/LPYHI5BLKSH3IP6NT2HKU3JFRN.json","graph_json":"https://pith.science/api/pith-number/LPYHI5BLKSH3IP6NT2HKU3JFRN/graph.json","events_json":"https://pith.science/api/pith-number/LPYHI5BLKSH3IP6NT2HKU3JFRN/events.json","paper":"https://pith.science/paper/LPYHI5BL"},"agent_actions":{"view_html":"https://pith.science/pith/LPYHI5BLKSH3IP6NT2HKU3JFRN","download_json":"https://pith.science/pith/LPYHI5BLKSH3IP6NT2HKU3JFRN.json","view_paper":"https://pith.science/paper/LPYHI5BL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.09061&json=true","fetch_graph":"https://pith.science/api/pith-number/LPYHI5BLKSH3IP6NT2HKU3JFRN/graph.json","fetch_events":"https://pith.science/api/pith-number/LPYHI5BLKSH3IP6NT2HKU3JFRN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LPYHI5BLKSH3IP6NT2HKU3JFRN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LPYHI5BLKSH3IP6NT2HKU3JFRN/action/storage_attestation","attest_author":"https://pith.science/pith/LPYHI5BLKSH3IP6NT2HKU3JFRN/action/author_attestation","sign_citation":"https://pith.science/pith/LPYHI5BLKSH3IP6NT2HKU3JFRN/action/citation_signature","submit_replication":"https://pith.science/pith/LPYHI5BLKSH3IP6NT2HKU3JFRN/action/replication_record"}},"created_at":"2026-07-05T08:09:22.161664+00:00","updated_at":"2026-07-05T08:09:22.161664+00:00"}