{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6TUBGWPC74QW7YQQY775V65AXR","short_pith_number":"pith:6TUBGWPC","schema_version":"1.0","canonical_sha256":"f4e81359e2ff216fe210c7ffdafba0bc5cd975f211289188a18e19d4cb27fc3d","source":{"kind":"arxiv","id":"2304.00685","version":2},"attestation_state":"computed","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"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2304.00685","created_at":"2026-07-05T07:45:45.870741+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.00685v2","created_at":"2026-07-05T07:45:45.870741+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.00685","created_at":"2026-07-05T07:45:45.870741+00:00"},{"alias_kind":"pith_short_12","alias_value":"6TUBGWPC74QW","created_at":"2026-07-05T07:45:45.870741+00:00"},{"alias_kind":"pith_short_16","alias_value":"6TUBGWPC74QW7YQQ","created_at":"2026-07-05T07:45:45.870741+00:00"},{"alias_kind":"pith_short_8","alias_value":"6TUBGWPC","created_at":"2026-07-05T07:45:45.870741+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26734","citing_title":"Robust Onion: Peeling Open Vocab Object Detectors Under Noise","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26734","citing_title":"Robust Onion: Peeling Open Vocab Object Detectors Under Noise","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20648","citing_title":"Jointly Learning Predicates and Actions Enables Zero-Shot Skill Composition","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04227","citing_title":"Mobile GUI Agents under Real-world Threats: Are We There Yet?","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2508.08508","citing_title":"Re:Verse -- Can Your VLM Read a Manga?","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6TUBGWPC74QW7YQQY775V65AXR","json":"https://pith.science/pith/6TUBGWPC74QW7YQQY775V65AXR.json","graph_json":"https://pith.science/api/pith-number/6TUBGWPC74QW7YQQY775V65AXR/graph.json","events_json":"https://pith.science/api/pith-number/6TUBGWPC74QW7YQQY775V65AXR/events.json","paper":"https://pith.science/paper/6TUBGWPC"},"agent_actions":{"view_html":"https://pith.science/pith/6TUBGWPC74QW7YQQY775V65AXR","download_json":"https://pith.science/pith/6TUBGWPC74QW7YQQY775V65AXR.json","view_paper":"https://pith.science/paper/6TUBGWPC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.00685&json=true","fetch_graph":"https://pith.science/api/pith-number/6TUBGWPC74QW7YQQY775V65AXR/graph.json","fetch_events":"https://pith.science/api/pith-number/6TUBGWPC74QW7YQQY775V65AXR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6TUBGWPC74QW7YQQY775V65AXR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6TUBGWPC74QW7YQQY775V65AXR/action/storage_attestation","attest_author":"https://pith.science/pith/6TUBGWPC74QW7YQQY775V65AXR/action/author_attestation","sign_citation":"https://pith.science/pith/6TUBGWPC74QW7YQQY775V65AXR/action/citation_signature","submit_replication":"https://pith.science/pith/6TUBGWPC74QW7YQQY775V65AXR/action/replication_record"}},"created_at":"2026-07-05T07:45:45.870741+00:00","updated_at":"2026-07-05T07:45:45.870741+00:00"}