{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PWGZEE43PJL6PUWR4U3GFLLCHL","short_pith_number":"pith:PWGZEE43","schema_version":"1.0","canonical_sha256":"7d8d92139b7a57e7d2d1e53662ad623aee1beba3d2bf0582ab68d0621326f933","source":{"kind":"arxiv","id":"2311.15732","version":2},"attestation_state":"computed","paper":{"title":"GPT4Vis: What Can GPT-4 Do for Zero-shot Visual Recognition?","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huanjin Yao, Jingdong Wang, Mengxi Zhang, Wanli Ouyang, Wenhao Wu, Yuxin Song","submitted_at":"2023-11-27T11:29:10Z","abstract_excerpt":"This paper does not present a novel method. Instead, it delves into an essential, yet must-know baseline in light of the latest advancements in Generative Artificial Intelligence (GenAI): the utilization of GPT-4 for visual understanding. Our study centers on the evaluation of GPT-4's linguistic and visual capabilities in zero-shot visual recognition tasks: Firstly, we explore the potential of its generated rich textual descriptions across various categories to enhance recognition performance without any training. Secondly, we evaluate GPT-4's visual proficiency in directly recognizing diverse"},"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":"2311.15732","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-27T11:29:10Z","cross_cats_sorted":[],"title_canon_sha256":"bcb49e0e7b99b7d7b4313ee135f7bd3bb51653140470172d5049eb928bbecfcd","abstract_canon_sha256":"ae6cac9471d242e639a3238ce4bad316d67993d77ae2f21fa9d26d77f8e44e03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:53.267035Z","signature_b64":"U+WAzrmqFfHur6FX2m/P48z7ORSuIylzyguJPE7Qr7uXlBkKabtv5jrgb3DsiuV67Z+QPjReAuGc76B5lKK4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d8d92139b7a57e7d2d1e53662ad623aee1beba3d2bf0582ab68d0621326f933","last_reissued_at":"2026-07-05T07:54:53.266626Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:53.266626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GPT4Vis: What Can GPT-4 Do for Zero-shot Visual Recognition?","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huanjin Yao, Jingdong Wang, Mengxi Zhang, Wanli Ouyang, Wenhao Wu, Yuxin Song","submitted_at":"2023-11-27T11:29:10Z","abstract_excerpt":"This paper does not present a novel method. Instead, it delves into an essential, yet must-know baseline in light of the latest advancements in Generative Artificial Intelligence (GenAI): the utilization of GPT-4 for visual understanding. Our study centers on the evaluation of GPT-4's linguistic and visual capabilities in zero-shot visual recognition tasks: Firstly, we explore the potential of its generated rich textual descriptions across various categories to enhance recognition performance without any training. Secondly, we evaluate GPT-4's visual proficiency in directly recognizing diverse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.15732","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/2311.15732/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":"2311.15732","created_at":"2026-07-05T07:54:53.266685+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.15732v2","created_at":"2026-07-05T07:54:53.266685+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.15732","created_at":"2026-07-05T07:54:53.266685+00:00"},{"alias_kind":"pith_short_12","alias_value":"PWGZEE43PJL6","created_at":"2026-07-05T07:54:53.266685+00:00"},{"alias_kind":"pith_short_16","alias_value":"PWGZEE43PJL6PUWR","created_at":"2026-07-05T07:54:53.266685+00:00"},{"alias_kind":"pith_short_8","alias_value":"PWGZEE43","created_at":"2026-07-05T07:54:53.266685+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11875","citing_title":"I Understand How You Feel: Enhancing Deeper Emotional Support Through Multilingual Emotional Validation in Dialogue System","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00684","citing_title":"AdaBoosting Text Prompts for Vision-Language Models","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2403.13805","citing_title":"RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition","ref_index":50,"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":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PWGZEE43PJL6PUWR4U3GFLLCHL","json":"https://pith.science/pith/PWGZEE43PJL6PUWR4U3GFLLCHL.json","graph_json":"https://pith.science/api/pith-number/PWGZEE43PJL6PUWR4U3GFLLCHL/graph.json","events_json":"https://pith.science/api/pith-number/PWGZEE43PJL6PUWR4U3GFLLCHL/events.json","paper":"https://pith.science/paper/PWGZEE43"},"agent_actions":{"view_html":"https://pith.science/pith/PWGZEE43PJL6PUWR4U3GFLLCHL","download_json":"https://pith.science/pith/PWGZEE43PJL6PUWR4U3GFLLCHL.json","view_paper":"https://pith.science/paper/PWGZEE43","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.15732&json=true","fetch_graph":"https://pith.science/api/pith-number/PWGZEE43PJL6PUWR4U3GFLLCHL/graph.json","fetch_events":"https://pith.science/api/pith-number/PWGZEE43PJL6PUWR4U3GFLLCHL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PWGZEE43PJL6PUWR4U3GFLLCHL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PWGZEE43PJL6PUWR4U3GFLLCHL/action/storage_attestation","attest_author":"https://pith.science/pith/PWGZEE43PJL6PUWR4U3GFLLCHL/action/author_attestation","sign_citation":"https://pith.science/pith/PWGZEE43PJL6PUWR4U3GFLLCHL/action/citation_signature","submit_replication":"https://pith.science/pith/PWGZEE43PJL6PUWR4U3GFLLCHL/action/replication_record"}},"created_at":"2026-07-05T07:54:53.266685+00:00","updated_at":"2026-07-05T07:54:53.266685+00:00"}