{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LIBXGDPWGI5AGGSUMEVYS5ETF3","short_pith_number":"pith:LIBXGDPW","schema_version":"1.0","canonical_sha256":"5a03730df6323a031a54612b8974932ef8d7812d8df992bb0963eb32a56d9949","source":{"kind":"arxiv","id":"2202.10936","version":2},"attestation_state":"computed","paper":{"title":"A Survey of Vision-Language Pre-Trained Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Junyi Li, Wayne Xin Zhao, Yifan Du, Zikang Liu","submitted_at":"2022-02-18T15:15:46Z","abstract_excerpt":"As transformer evolves, pre-trained models have advanced at a breakneck pace in recent years. They have dominated the mainstream techniques in natural language processing (NLP) and computer vision (CV). How to adapt pre-training to the field of Vision-and-Language (V-L) learning and improve downstream task performance becomes a focus of multimodal learning. In this paper, we review the recent progress in Vision-Language Pre-Trained Models (VL-PTMs). As the core content, we first briefly introduce several ways to encode raw images and texts to single-modal embeddings before pre-training. Then, "},"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":"2202.10936","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-18T15:15:46Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"b2d7c3a989b8621a656a9d347dd051f41b6ec0ff28db05257fba489dfb5c7cfb","abstract_canon_sha256":"c5b48b61929d58c21430880f12d9eca67e55b967d0a9927fcefc3049fe3af78f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:40:50.651167Z","signature_b64":"mvAQMSssM2JOvhQnhfUCDkHAhfgHe5s2j9P5RAdDCmEPlfp5dgFhI50CVEk41QoxP2JxFoeKv1OKLjOp7J/CAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a03730df6323a031a54612b8974932ef8d7812d8df992bb0963eb32a56d9949","last_reissued_at":"2026-07-05T04:40:50.650699Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:40:50.650699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of Vision-Language Pre-Trained Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Junyi Li, Wayne Xin Zhao, Yifan Du, Zikang Liu","submitted_at":"2022-02-18T15:15:46Z","abstract_excerpt":"As transformer evolves, pre-trained models have advanced at a breakneck pace in recent years. They have dominated the mainstream techniques in natural language processing (NLP) and computer vision (CV). How to adapt pre-training to the field of Vision-and-Language (V-L) learning and improve downstream task performance becomes a focus of multimodal learning. In this paper, we review the recent progress in Vision-Language Pre-Trained Models (VL-PTMs). As the core content, we first briefly introduce several ways to encode raw images and texts to single-modal embeddings before pre-training. Then, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.10936","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/2202.10936/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":"2202.10936","created_at":"2026-07-05T04:40:50.650759+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.10936v2","created_at":"2026-07-05T04:40:50.650759+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.10936","created_at":"2026-07-05T04:40:50.650759+00:00"},{"alias_kind":"pith_short_12","alias_value":"LIBXGDPWGI5A","created_at":"2026-07-05T04:40:50.650759+00:00"},{"alias_kind":"pith_short_16","alias_value":"LIBXGDPWGI5AGGSU","created_at":"2026-07-05T04:40:50.650759+00:00"},{"alias_kind":"pith_short_8","alias_value":"LIBXGDPW","created_at":"2026-07-05T04:40:50.650759+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11637","citing_title":"TouchThinker: Scaling Tactile Commonsense Reasoning to the Open World with Large-scale Data and Action-aware Representation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2508.10016","citing_title":"Training-Free Multimodal Large Language Model Orchestration","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2508.04227","citing_title":"Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2508.10016","citing_title":"Training-Free Multimodal Large Language Model Orchestration","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08273","citing_title":"Efficient Prompt Learning for Traffic Forecasting","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08869","citing_title":"Horizontal and Longitudinal Comparisons Among AI Subfields: A Bibliometric Perspective","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22885","citing_title":"Federated Cross-Modal Retrieval with Missing Modalities via Semantic Routing and Adapter Personalization","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01359","citing_title":"Structural Ranking of the Cognitive Plausibility of Computational Models of Analogy and Metaphors with the Minimal Cognitive Grid","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12890","citing_title":"Towards Long-horizon Agentic Multimodal Search","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04563","citing_title":"Temporal Inversion for Learning Interval Change in Chest X-Rays","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LIBXGDPWGI5AGGSUMEVYS5ETF3","json":"https://pith.science/pith/LIBXGDPWGI5AGGSUMEVYS5ETF3.json","graph_json":"https://pith.science/api/pith-number/LIBXGDPWGI5AGGSUMEVYS5ETF3/graph.json","events_json":"https://pith.science/api/pith-number/LIBXGDPWGI5AGGSUMEVYS5ETF3/events.json","paper":"https://pith.science/paper/LIBXGDPW"},"agent_actions":{"view_html":"https://pith.science/pith/LIBXGDPWGI5AGGSUMEVYS5ETF3","download_json":"https://pith.science/pith/LIBXGDPWGI5AGGSUMEVYS5ETF3.json","view_paper":"https://pith.science/paper/LIBXGDPW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.10936&json=true","fetch_graph":"https://pith.science/api/pith-number/LIBXGDPWGI5AGGSUMEVYS5ETF3/graph.json","fetch_events":"https://pith.science/api/pith-number/LIBXGDPWGI5AGGSUMEVYS5ETF3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LIBXGDPWGI5AGGSUMEVYS5ETF3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LIBXGDPWGI5AGGSUMEVYS5ETF3/action/storage_attestation","attest_author":"https://pith.science/pith/LIBXGDPWGI5AGGSUMEVYS5ETF3/action/author_attestation","sign_citation":"https://pith.science/pith/LIBXGDPWGI5AGGSUMEVYS5ETF3/action/citation_signature","submit_replication":"https://pith.science/pith/LIBXGDPWGI5AGGSUMEVYS5ETF3/action/replication_record"}},"created_at":"2026-07-05T04:40:50.650759+00:00","updated_at":"2026-07-05T04:40:50.650759+00:00"}