{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6TUBGWPC74QW7YQQY775V65AXR","short_pith_number":"pith:6TUBGWPC","canonical_record":{"source":{"id":"2304.00685","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-03T02:17:05Z","cross_cats_sorted":[],"title_canon_sha256":"7829bb449255877509d511373bd7eae38932fdcf800daa6f9ef2242600b463a3","abstract_canon_sha256":"fd2f5084922b113b277b53f8e32b85c57bdd9eb83327f9cf734fd145b8ada286"},"schema_version":"1.0"},"canonical_sha256":"f4e81359e2ff216fe210c7ffdafba0bc5cd975f211289188a18e19d4cb27fc3d","source":{"kind":"arxiv","id":"2304.00685","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.00685","created_at":"2026-07-05T07:45:45Z"},{"alias_kind":"arxiv_version","alias_value":"2304.00685v2","created_at":"2026-07-05T07:45:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.00685","created_at":"2026-07-05T07:45:45Z"},{"alias_kind":"pith_short_12","alias_value":"6TUBGWPC74QW","created_at":"2026-07-05T07:45:45Z"},{"alias_kind":"pith_short_16","alias_value":"6TUBGWPC74QW7YQQ","created_at":"2026-07-05T07:45:45Z"},{"alias_kind":"pith_short_8","alias_value":"6TUBGWPC","created_at":"2026-07-05T07:45:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6TUBGWPC74QW7YQQY775V65AXR","target":"record","payload":{"canonical_record":{"source":{"id":"2304.00685","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-03T02:17:05Z","cross_cats_sorted":[],"title_canon_sha256":"7829bb449255877509d511373bd7eae38932fdcf800daa6f9ef2242600b463a3","abstract_canon_sha256":"fd2f5084922b113b277b53f8e32b85c57bdd9eb83327f9cf734fd145b8ada286"},"schema_version":"1.0"},"canonical_sha256":"f4e81359e2ff216fe210c7ffdafba0bc5cd975f211289188a18e19d4cb27fc3d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:45.871118Z","signature_b64":"fgFSfEzC9GxgriIx8RJczJu5+iNaM4y3PcpbVQAxhAeEg0W/1gDhnSAVOvyGH+gdet1qedGrBJprq9t0tTkIBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4e81359e2ff216fe210c7ffdafba0bc5cd975f211289188a18e19d4cb27fc3d","last_reissued_at":"2026-07-05T07:45:45.870682Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:45.870682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.00685","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:45:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BLk4Pddmg5IEyYpFDnKMxpNHPDJZagIh8tW843Ntouo563QlKGZuZTV0noG0EunuqBpRO2QkIC3xxNxB8IaWAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:58:31.982887Z"},"content_sha256":"a5be247193d8d295c6974e0c7102f7a3a33f9ee80d15bf78af3efbb47ab02031","schema_version":"1.0","event_id":"sha256:a5be247193d8d295c6974e0c7102f7a3a33f9ee80d15bf78af3efbb47ab02031"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6TUBGWPC74QW7YQQY775V65AXR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vision-Language Models for Vision Tasks: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaxing Huang, Jingyi Zhang, Sheng Jin, Shijian Lu","submitted_at":"2023-04-03T02:17:05Z","abstract_excerpt":"Most visual recognition studies rely heavily on crowd-labelled data in deep neural networks (DNNs) training, and they usually train a DNN for each single visual recognition task, leading to a laborious and time-consuming visual recognition paradigm. To address the two challenges, Vision-Language Models (VLMs) have been intensively investigated recently, which learns rich vision-language correlation from web-scale image-text pairs that are almost infinitely available on the Internet and enables zero-shot predictions on various visual recognition tasks with a single VLM. This paper provides a sy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.00685","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/2304.00685/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":"2026-07-05T07:45:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6WBPKyO+gWJR7BbTK46ykQ4EKbLjQb3NAT9Si1pSXtXs305Ec1/Lc3jkDi7PtdlfxO33QrGciQ+gEeF/bZASCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:58:31.983428Z"},"content_sha256":"51a120300c7df66df13ba5315fc701ffeeb9684a0c7f93baead30878c702fce2","schema_version":"1.0","event_id":"sha256:51a120300c7df66df13ba5315fc701ffeeb9684a0c7f93baead30878c702fce2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6TUBGWPC74QW7YQQY775V65AXR/bundle.json","state_url":"https://pith.science/pith/6TUBGWPC74QW7YQQY775V65AXR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6TUBGWPC74QW7YQQY775V65AXR/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":"2026-08-06T19:58:31Z","links":{"resolver":"https://pith.science/pith/6TUBGWPC74QW7YQQY775V65AXR","bundle":"https://pith.science/pith/6TUBGWPC74QW7YQQY775V65AXR/bundle.json","state":"https://pith.science/pith/6TUBGWPC74QW7YQQY775V65AXR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6TUBGWPC74QW7YQQY775V65AXR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6TUBGWPC74QW7YQQY775V65AXR","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":"fd2f5084922b113b277b53f8e32b85c57bdd9eb83327f9cf734fd145b8ada286","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-03T02:17:05Z","title_canon_sha256":"7829bb449255877509d511373bd7eae38932fdcf800daa6f9ef2242600b463a3"},"schema_version":"1.0","source":{"id":"2304.00685","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.00685","created_at":"2026-07-05T07:45:45Z"},{"alias_kind":"arxiv_version","alias_value":"2304.00685v2","created_at":"2026-07-05T07:45:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.00685","created_at":"2026-07-05T07:45:45Z"},{"alias_kind":"pith_short_12","alias_value":"6TUBGWPC74QW","created_at":"2026-07-05T07:45:45Z"},{"alias_kind":"pith_short_16","alias_value":"6TUBGWPC74QW7YQQ","created_at":"2026-07-05T07:45:45Z"},{"alias_kind":"pith_short_8","alias_value":"6TUBGWPC","created_at":"2026-07-05T07:45:45Z"}],"graph_snapshots":[{"event_id":"sha256:51a120300c7df66df13ba5315fc701ffeeb9684a0c7f93baead30878c702fce2","target":"graph","created_at":"2026-07-05T07:45:45Z","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/2304.00685/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most visual recognition studies rely heavily on crowd-labelled data in deep neural networks (DNNs) training, and they usually train a DNN for each single visual recognition task, leading to a laborious and time-consuming visual recognition paradigm. To address the two challenges, Vision-Language Models (VLMs) have been intensively investigated recently, which learns rich vision-language correlation from web-scale image-text pairs that are almost infinitely available on the Internet and enables zero-shot predictions on various visual recognition tasks with a single VLM. This paper provides a sy","authors_text":"Jiaxing Huang, Jingyi Zhang, Sheng Jin, Shijian Lu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-03T02:17:05Z","title":"Vision-Language Models for Vision Tasks: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.00685","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:a5be247193d8d295c6974e0c7102f7a3a33f9ee80d15bf78af3efbb47ab02031","target":"record","created_at":"2026-07-05T07:45:45Z","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":"fd2f5084922b113b277b53f8e32b85c57bdd9eb83327f9cf734fd145b8ada286","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-03T02:17:05Z","title_canon_sha256":"7829bb449255877509d511373bd7eae38932fdcf800daa6f9ef2242600b463a3"},"schema_version":"1.0","source":{"id":"2304.00685","kind":"arxiv","version":2}},"canonical_sha256":"f4e81359e2ff216fe210c7ffdafba0bc5cd975f211289188a18e19d4cb27fc3d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4e81359e2ff216fe210c7ffdafba0bc5cd975f211289188a18e19d4cb27fc3d","first_computed_at":"2026-07-05T07:45:45.870682Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:45:45.870682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fgFSfEzC9GxgriIx8RJczJu5+iNaM4y3PcpbVQAxhAeEg0W/1gDhnSAVOvyGH+gdet1qedGrBJprq9t0tTkIBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:45:45.871118Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.00685","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5be247193d8d295c6974e0c7102f7a3a33f9ee80d15bf78af3efbb47ab02031","sha256:51a120300c7df66df13ba5315fc701ffeeb9684a0c7f93baead30878c702fce2"],"state_sha256":"599cf7f148b85eb9d78671f032572b1a994a2d97a71722f962f935a19eac6502"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+Tpd6EAZQcVFGFy3Xh6eiX+Rs3n7zCIX2mV6Py9lMbMQrYB5cmV+DnT+N2yoOEMnT7WunbaUhL4qqQu7r/VNDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T19:58:31.988080Z","bundle_sha256":"1deebcb90fe45e8ea1e434162c0d4496052df9e647c2d6da4e7f8f88b0dfe6e4"}}