{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QMCHEBIEDHT7ILGSADCZIOINIZ","short_pith_number":"pith:QMCHEBIE","schema_version":"1.0","canonical_sha256":"830472050419e7f42cd200c594390d4662ac08d3464d2ef6e989c3b480e85575","source":{"kind":"arxiv","id":"2306.02243","version":3},"attestation_state":"computed","paper":{"title":"Retrieval-Enhanced Visual Prompt Learning for Few-shot Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Chen, Jintao Rong, Linlin Ou, Tianxiao Chen, Xinyi Yu, Yifan Liu","submitted_at":"2023-06-04T03:06:37Z","abstract_excerpt":"The Contrastive Language-Image Pretraining (CLIP) model has been widely used in various downstream vision tasks. The few-shot learning paradigm has been widely adopted to augment its capacity for these tasks. However, current paradigms may struggle with fine-grained classification, such as satellite image recognition, due to widening domain gaps. To address this limitation, we propose retrieval-enhanced visual prompt learning (RePrompt), which introduces retrieval mechanisms to cache and reuse the knowledge of downstream tasks. RePrompt constructs a retrieval database from either training exam"},"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":"2306.02243","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-04T03:06:37Z","cross_cats_sorted":[],"title_canon_sha256":"f037775ed35488dea3136f5462b352176d242c81a412f8b0e6aa856ffab6042c","abstract_canon_sha256":"2a522e2714280a76072865f0a54d3199ae489892ca94a79cc1cca6d73f13f4b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:20.753609Z","signature_b64":"hjJ1k63CqgghnMfDPqxgdtFH1TF6QQeqiMUjMcd7Jil88PUXResMbZP0jJSxCqAYammodwawYB9/oPNh4nf3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"830472050419e7f42cd200c594390d4662ac08d3464d2ef6e989c3b480e85575","last_reissued_at":"2026-07-05T09:38:20.753120Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:20.753120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieval-Enhanced Visual Prompt Learning for Few-shot Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Chen, Jintao Rong, Linlin Ou, Tianxiao Chen, Xinyi Yu, Yifan Liu","submitted_at":"2023-06-04T03:06:37Z","abstract_excerpt":"The Contrastive Language-Image Pretraining (CLIP) model has been widely used in various downstream vision tasks. The few-shot learning paradigm has been widely adopted to augment its capacity for these tasks. However, current paradigms may struggle with fine-grained classification, such as satellite image recognition, due to widening domain gaps. To address this limitation, we propose retrieval-enhanced visual prompt learning (RePrompt), which introduces retrieval mechanisms to cache and reuse the knowledge of downstream tasks. RePrompt constructs a retrieval database from either training exam"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02243","kind":"arxiv","version":3},"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/2306.02243/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":"2306.02243","created_at":"2026-07-05T09:38:20.753177+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.02243v3","created_at":"2026-07-05T09:38:20.753177+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02243","created_at":"2026-07-05T09:38:20.753177+00:00"},{"alias_kind":"pith_short_12","alias_value":"QMCHEBIEDHT7","created_at":"2026-07-05T09:38:20.753177+00:00"},{"alias_kind":"pith_short_16","alias_value":"QMCHEBIEDHT7ILGS","created_at":"2026-07-05T09:38:20.753177+00:00"},{"alias_kind":"pith_short_8","alias_value":"QMCHEBIE","created_at":"2026-07-05T09:38:20.753177+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.04227","citing_title":"Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QMCHEBIEDHT7ILGSADCZIOINIZ","json":"https://pith.science/pith/QMCHEBIEDHT7ILGSADCZIOINIZ.json","graph_json":"https://pith.science/api/pith-number/QMCHEBIEDHT7ILGSADCZIOINIZ/graph.json","events_json":"https://pith.science/api/pith-number/QMCHEBIEDHT7ILGSADCZIOINIZ/events.json","paper":"https://pith.science/paper/QMCHEBIE"},"agent_actions":{"view_html":"https://pith.science/pith/QMCHEBIEDHT7ILGSADCZIOINIZ","download_json":"https://pith.science/pith/QMCHEBIEDHT7ILGSADCZIOINIZ.json","view_paper":"https://pith.science/paper/QMCHEBIE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.02243&json=true","fetch_graph":"https://pith.science/api/pith-number/QMCHEBIEDHT7ILGSADCZIOINIZ/graph.json","fetch_events":"https://pith.science/api/pith-number/QMCHEBIEDHT7ILGSADCZIOINIZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QMCHEBIEDHT7ILGSADCZIOINIZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QMCHEBIEDHT7ILGSADCZIOINIZ/action/storage_attestation","attest_author":"https://pith.science/pith/QMCHEBIEDHT7ILGSADCZIOINIZ/action/author_attestation","sign_citation":"https://pith.science/pith/QMCHEBIEDHT7ILGSADCZIOINIZ/action/citation_signature","submit_replication":"https://pith.science/pith/QMCHEBIEDHT7ILGSADCZIOINIZ/action/replication_record"}},"created_at":"2026-07-05T09:38:20.753177+00:00","updated_at":"2026-07-05T09:38:20.753177+00:00"}