{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:2F7OTUZXOIJCYPF3O7MXCZBCPF","short_pith_number":"pith:2F7OTUZX","canonical_record":{"source":{"id":"2210.09263","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-17T17:11:36Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8e5f5af879e4e313ffc5f9a937562e132ef4dd6ff10d69c00a18ba6e558b6051","abstract_canon_sha256":"c9d0fb177ace286ee0c59951eb04a95bb069d3e529690fe57d24613ac47186e0"},"schema_version":"1.0"},"canonical_sha256":"d17ee9d33772122c3cbb77d9716422797a3831ce60ee38c4980c1435d7e378e4","source":{"kind":"arxiv","id":"2210.09263","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.09263","created_at":"2026-07-05T05:07:20Z"},{"alias_kind":"arxiv_version","alias_value":"2210.09263v1","created_at":"2026-07-05T05:07:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.09263","created_at":"2026-07-05T05:07:20Z"},{"alias_kind":"pith_short_12","alias_value":"2F7OTUZXOIJC","created_at":"2026-07-05T05:07:20Z"},{"alias_kind":"pith_short_16","alias_value":"2F7OTUZXOIJCYPF3","created_at":"2026-07-05T05:07:20Z"},{"alias_kind":"pith_short_8","alias_value":"2F7OTUZX","created_at":"2026-07-05T05:07:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:2F7OTUZXOIJCYPF3O7MXCZBCPF","target":"record","payload":{"canonical_record":{"source":{"id":"2210.09263","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-17T17:11:36Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8e5f5af879e4e313ffc5f9a937562e132ef4dd6ff10d69c00a18ba6e558b6051","abstract_canon_sha256":"c9d0fb177ace286ee0c59951eb04a95bb069d3e529690fe57d24613ac47186e0"},"schema_version":"1.0"},"canonical_sha256":"d17ee9d33772122c3cbb77d9716422797a3831ce60ee38c4980c1435d7e378e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:07:20.662225Z","signature_b64":"cS2zqlDJJ6CFXGBBuWn2oVnTIte6RVoAXYn3y7Vf/qSUS0U+N8ByhS5d4xVgX2BTrURGul5iiCfkqJSGIU5aCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d17ee9d33772122c3cbb77d9716422797a3831ce60ee38c4980c1435d7e378e4","last_reissued_at":"2026-07-05T05:07:20.661758Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:07:20.661758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.09263","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:07:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fKBzyGRmSRtITw8wJj50VMwsjz3NidF+BblyMIOAyYA5YmjatwOVUPEPZSquoDx8bvVE/fsvNGrHCi0175UJBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:59:21.313579Z"},"content_sha256":"6aadb939d0eb877732f63edc58330ded8458226591edca95304f1d4133e37a76","schema_version":"1.0","event_id":"sha256:6aadb939d0eb877732f63edc58330ded8458226591edca95304f1d4133e37a76"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:2F7OTUZXOIJCYPF3O7MXCZBCPF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vision-Language Pre-training: Basics, Recent Advances, and Future Trends","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chunyuan Li, Jianfeng Gao, Lijuan Wang, Linjie Li, Zhe Gan, Zicheng Liu","submitted_at":"2022-10-17T17:11:36Z","abstract_excerpt":"This paper surveys vision-language pre-training (VLP) methods for multimodal intelligence that have been developed in the last few years. We group these approaches into three categories: ($i$) VLP for image-text tasks, such as image captioning, image-text retrieval, visual question answering, and visual grounding; ($ii$) VLP for core computer vision tasks, such as (open-set) image classification, object detection, and segmentation; and ($iii$) VLP for video-text tasks, such as video captioning, video-text retrieval, and video question answering. For each category, we present a comprehensive re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.09263","kind":"arxiv","version":1},"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/2210.09263/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:07:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RXZkclWv8eWEGQzCVybG/lypLGCvokTVmJk/Q0/MncrMOZ9UTj5OMHa1v45Ur8ozZczT3HqMRwUbpmBBEO3EBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:59:21.314079Z"},"content_sha256":"5a84eec7502b1b362726e62342eb690de7c223eae6b4705a22335e93c505a684","schema_version":"1.0","event_id":"sha256:5a84eec7502b1b362726e62342eb690de7c223eae6b4705a22335e93c505a684"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2F7OTUZXOIJCYPF3O7MXCZBCPF/bundle.json","state_url":"https://pith.science/pith/2F7OTUZXOIJCYPF3O7MXCZBCPF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2F7OTUZXOIJCYPF3O7MXCZBCPF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T06:59:21Z","links":{"resolver":"https://pith.science/pith/2F7OTUZXOIJCYPF3O7MXCZBCPF","bundle":"https://pith.science/pith/2F7OTUZXOIJCYPF3O7MXCZBCPF/bundle.json","state":"https://pith.science/pith/2F7OTUZXOIJCYPF3O7MXCZBCPF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2F7OTUZXOIJCYPF3O7MXCZBCPF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2F7OTUZXOIJCYPF3O7MXCZBCPF","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":"c9d0fb177ace286ee0c59951eb04a95bb069d3e529690fe57d24613ac47186e0","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-17T17:11:36Z","title_canon_sha256":"8e5f5af879e4e313ffc5f9a937562e132ef4dd6ff10d69c00a18ba6e558b6051"},"schema_version":"1.0","source":{"id":"2210.09263","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.09263","created_at":"2026-07-05T05:07:20Z"},{"alias_kind":"arxiv_version","alias_value":"2210.09263v1","created_at":"2026-07-05T05:07:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.09263","created_at":"2026-07-05T05:07:20Z"},{"alias_kind":"pith_short_12","alias_value":"2F7OTUZXOIJC","created_at":"2026-07-05T05:07:20Z"},{"alias_kind":"pith_short_16","alias_value":"2F7OTUZXOIJCYPF3","created_at":"2026-07-05T05:07:20Z"},{"alias_kind":"pith_short_8","alias_value":"2F7OTUZX","created_at":"2026-07-05T05:07:20Z"}],"graph_snapshots":[{"event_id":"sha256:5a84eec7502b1b362726e62342eb690de7c223eae6b4705a22335e93c505a684","target":"graph","created_at":"2026-07-05T05:07:20Z","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/2210.09263/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper surveys vision-language pre-training (VLP) methods for multimodal intelligence that have been developed in the last few years. We group these approaches into three categories: ($i$) VLP for image-text tasks, such as image captioning, image-text retrieval, visual question answering, and visual grounding; ($ii$) VLP for core computer vision tasks, such as (open-set) image classification, object detection, and segmentation; and ($iii$) VLP for video-text tasks, such as video captioning, video-text retrieval, and video question answering. For each category, we present a comprehensive re","authors_text":"Chunyuan Li, Jianfeng Gao, Lijuan Wang, Linjie Li, Zhe Gan, Zicheng Liu","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-17T17:11:36Z","title":"Vision-Language Pre-training: Basics, Recent Advances, and Future Trends"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.09263","kind":"arxiv","version":1},"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":"sha256:6aadb939d0eb877732f63edc58330ded8458226591edca95304f1d4133e37a76","target":"record","created_at":"2026-07-05T05:07:20Z","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":"c9d0fb177ace286ee0c59951eb04a95bb069d3e529690fe57d24613ac47186e0","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-17T17:11:36Z","title_canon_sha256":"8e5f5af879e4e313ffc5f9a937562e132ef4dd6ff10d69c00a18ba6e558b6051"},"schema_version":"1.0","source":{"id":"2210.09263","kind":"arxiv","version":1}},"canonical_sha256":"d17ee9d33772122c3cbb77d9716422797a3831ce60ee38c4980c1435d7e378e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d17ee9d33772122c3cbb77d9716422797a3831ce60ee38c4980c1435d7e378e4","first_computed_at":"2026-07-05T05:07:20.661758Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:07:20.661758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cS2zqlDJJ6CFXGBBuWn2oVnTIte6RVoAXYn3y7Vf/qSUS0U+N8ByhS5d4xVgX2BTrURGul5iiCfkqJSGIU5aCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:07:20.662225Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.09263","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6aadb939d0eb877732f63edc58330ded8458226591edca95304f1d4133e37a76","sha256:5a84eec7502b1b362726e62342eb690de7c223eae6b4705a22335e93c505a684"],"state_sha256":"0d8e8221032968dc8d9e4dd786c7ba9eee9cac41cacd0b73282551acb53c83b7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M/C4TVPUW+hHX+tK/YXjj+X/QhaGdeIanK+hGW+USkhXvl5WwUlnxsWG1S7Llbm0bih9Z1VspenLLdMJrr8ODg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T06:59:21.320164Z","bundle_sha256":"914122aba71fd85fd3d64fc75036a183e0825329729186862e56c9c935c73c1b"}}