{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RUXMYVONTWFPWRH4LSEFZ2XLPT","short_pith_number":"pith:RUXMYVON","schema_version":"1.0","canonical_sha256":"8d2ecc55cd9d8afb44fc5c885ceaeb7ccb984db3041ceb819bad5f960fc5bd08","source":{"kind":"arxiv","id":"2312.04076","version":2},"attestation_state":"computed","paper":{"title":"Large Language Models are Good Prompt Learners for Low-Shot Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haidong Zhu, Jingmin Wei, Ram Nevatia, Xuefeng Hu, Zhaoheng Zheng","submitted_at":"2023-12-07T06:43:34Z","abstract_excerpt":"Low-shot image classification, where training images are limited or inaccessible, has benefited from recent progress on pre-trained vision-language (VL) models with strong generalizability, e.g. CLIP. Prompt learning methods built with VL models generate text features from the class names that only have confined class-specific information. Large Language Models (LLMs), with their vast encyclopedic knowledge, emerge as the complement. Thus, in this paper, we discuss the integration of LLMs to enhance pre-trained VL models, specifically on low-shot classification. However, the domain gap between"},"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":"2312.04076","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-07T06:43:34Z","cross_cats_sorted":[],"title_canon_sha256":"e732c99de7f39abfc9cb66067d360bda75a466c05119acf67aded21a75311cc3","abstract_canon_sha256":"8d8bbcca47f91836aaf55d9f2c736d5ba56b3b14e82fb8757e3855800c124989"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:46.621474Z","signature_b64":"FwpqLw1NjmaXsLGS2uOjD7c3Qi7NfoAJQmyKQ7aKrLw1VeeOTK5RhqvPuBYmQSai02Jy9R8NZWS8jPh4FNw8AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d2ecc55cd9d8afb44fc5c885ceaeb7ccb984db3041ceb819bad5f960fc5bd08","last_reissued_at":"2026-07-05T08:03:46.620991Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:46.620991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models are Good Prompt Learners for Low-Shot Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haidong Zhu, Jingmin Wei, Ram Nevatia, Xuefeng Hu, Zhaoheng Zheng","submitted_at":"2023-12-07T06:43:34Z","abstract_excerpt":"Low-shot image classification, where training images are limited or inaccessible, has benefited from recent progress on pre-trained vision-language (VL) models with strong generalizability, e.g. CLIP. Prompt learning methods built with VL models generate text features from the class names that only have confined class-specific information. Large Language Models (LLMs), with their vast encyclopedic knowledge, emerge as the complement. Thus, in this paper, we discuss the integration of LLMs to enhance pre-trained VL models, specifically on low-shot classification. However, the domain gap between"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04076","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/2312.04076/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":"2312.04076","created_at":"2026-07-05T08:03:46.621048+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.04076v2","created_at":"2026-07-05T08:03:46.621048+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04076","created_at":"2026-07-05T08:03:46.621048+00:00"},{"alias_kind":"pith_short_12","alias_value":"RUXMYVONTWFP","created_at":"2026-07-05T08:03:46.621048+00:00"},{"alias_kind":"pith_short_16","alias_value":"RUXMYVONTWFPWRH4","created_at":"2026-07-05T08:03:46.621048+00:00"},{"alias_kind":"pith_short_8","alias_value":"RUXMYVON","created_at":"2026-07-05T08:03:46.621048+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.08410","citing_title":"Multi-modal Mutual-Guidance Conditional Prompt Learning for Vision-Language Models","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RUXMYVONTWFPWRH4LSEFZ2XLPT","json":"https://pith.science/pith/RUXMYVONTWFPWRH4LSEFZ2XLPT.json","graph_json":"https://pith.science/api/pith-number/RUXMYVONTWFPWRH4LSEFZ2XLPT/graph.json","events_json":"https://pith.science/api/pith-number/RUXMYVONTWFPWRH4LSEFZ2XLPT/events.json","paper":"https://pith.science/paper/RUXMYVON"},"agent_actions":{"view_html":"https://pith.science/pith/RUXMYVONTWFPWRH4LSEFZ2XLPT","download_json":"https://pith.science/pith/RUXMYVONTWFPWRH4LSEFZ2XLPT.json","view_paper":"https://pith.science/paper/RUXMYVON","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.04076&json=true","fetch_graph":"https://pith.science/api/pith-number/RUXMYVONTWFPWRH4LSEFZ2XLPT/graph.json","fetch_events":"https://pith.science/api/pith-number/RUXMYVONTWFPWRH4LSEFZ2XLPT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RUXMYVONTWFPWRH4LSEFZ2XLPT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RUXMYVONTWFPWRH4LSEFZ2XLPT/action/storage_attestation","attest_author":"https://pith.science/pith/RUXMYVONTWFPWRH4LSEFZ2XLPT/action/author_attestation","sign_citation":"https://pith.science/pith/RUXMYVONTWFPWRH4LSEFZ2XLPT/action/citation_signature","submit_replication":"https://pith.science/pith/RUXMYVONTWFPWRH4LSEFZ2XLPT/action/replication_record"}},"created_at":"2026-07-05T08:03:46.621048+00:00","updated_at":"2026-07-05T08:03:46.621048+00:00"}