{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LIBXGDPWGI5AGGSUMEVYS5ETF3","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":"c5b48b61929d58c21430880f12d9eca67e55b967d0a9927fcefc3049fe3af78f","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-18T15:15:46Z","title_canon_sha256":"b2d7c3a989b8621a656a9d347dd051f41b6ec0ff28db05257fba489dfb5c7cfb"},"schema_version":"1.0","source":{"id":"2202.10936","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.10936","created_at":"2026-07-05T04:40:50Z"},{"alias_kind":"arxiv_version","alias_value":"2202.10936v2","created_at":"2026-07-05T04:40:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.10936","created_at":"2026-07-05T04:40:50Z"},{"alias_kind":"pith_short_12","alias_value":"LIBXGDPWGI5A","created_at":"2026-07-05T04:40:50Z"},{"alias_kind":"pith_short_16","alias_value":"LIBXGDPWGI5AGGSU","created_at":"2026-07-05T04:40:50Z"},{"alias_kind":"pith_short_8","alias_value":"LIBXGDPW","created_at":"2026-07-05T04:40:50Z"}],"graph_snapshots":[{"event_id":"sha256:7a97bb6ff84de8545c8da6385c013f0d1885e48238e28d42b3277255b57733c2","target":"graph","created_at":"2026-07-05T04:40:50Z","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/2202.10936/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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, ","authors_text":"Junyi Li, Wayne Xin Zhao, Yifan Du, Zikang Liu","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-18T15:15:46Z","title":"A Survey of Vision-Language Pre-Trained Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.10936","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":"sha256:3ccb844493be20e11c6306009d49e13536b271f805f5ed2cc4cf4a54c9ab6076","target":"record","created_at":"2026-07-05T04:40:50Z","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":"c5b48b61929d58c21430880f12d9eca67e55b967d0a9927fcefc3049fe3af78f","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-18T15:15:46Z","title_canon_sha256":"b2d7c3a989b8621a656a9d347dd051f41b6ec0ff28db05257fba489dfb5c7cfb"},"schema_version":"1.0","source":{"id":"2202.10936","kind":"arxiv","version":2}},"canonical_sha256":"5a03730df6323a031a54612b8974932ef8d7812d8df992bb0963eb32a56d9949","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a03730df6323a031a54612b8974932ef8d7812d8df992bb0963eb32a56d9949","first_computed_at":"2026-07-05T04:40:50.650699Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:40:50.650699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mvAQMSssM2JOvhQnhfUCDkHAhfgHe5s2j9P5RAdDCmEPlfp5dgFhI50CVEk41QoxP2JxFoeKv1OKLjOp7J/CAg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:40:50.651167Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.10936","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ccb844493be20e11c6306009d49e13536b271f805f5ed2cc4cf4a54c9ab6076","sha256:7a97bb6ff84de8545c8da6385c013f0d1885e48238e28d42b3277255b57733c2"],"state_sha256":"58cb101c8ad563aacfcf659f15c64f9174c188efecf564a62bcc089313a48441"}