{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AHYK2ET5ZA7I4F2SHYQ47LHQCC","short_pith_number":"pith:AHYK2ET5","schema_version":"1.0","canonical_sha256":"01f0ad127dc83e8e17523e21cfacf0109e134d2e96e11d2c03f202d348eae573","source":{"kind":"arxiv","id":"2401.01736","version":2},"attestation_state":"computed","paper":{"title":"Few-shot Adaptation of Multi-modal Foundation Models: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Delong Chen, Fan Liu, Tianshu Zhang, Wenwen Cai, Wenwen Dai, Xiaocong Zhou","submitted_at":"2024-01-03T13:19:14Z","abstract_excerpt":"Multi-modal (vision-language) models, such as CLIP, are replacing traditional supervised pre-training models (e.g., ImageNet-based pre-training) as the new generation of visual foundation models. These models with robust and aligned semantic representations learned from billions of internet image-text pairs and can be applied to various downstream tasks in a zero-shot manner. However, in some fine-grained domains like medical imaging and remote sensing, the performance of multi-modal foundation models often leaves much to be desired. Consequently, many researchers have begun to explore few-sho"},"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":"2401.01736","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-03T13:19:14Z","cross_cats_sorted":[],"title_canon_sha256":"f511a7e91543ec5ca42fec965a715b0f36bb34fb4ed8e66b13727164da1db6bd","abstract_canon_sha256":"0cbd6a8609b77ef65e90a5f66295176bd2c639fe49e79dc8288d512ae0221c03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:07.848875Z","signature_b64":"GqBzEOftsMGuxGfxLVzVfFbHybf3rs2tCWIibDBmtaExQLbeqg7Fu1CbbLzdPv7lH9bW2u978bOaghs7AaptDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01f0ad127dc83e8e17523e21cfacf0109e134d2e96e11d2c03f202d348eae573","last_reissued_at":"2026-07-05T07:30:07.848482Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:07.848482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Few-shot Adaptation of Multi-modal Foundation Models: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Delong Chen, Fan Liu, Tianshu Zhang, Wenwen Cai, Wenwen Dai, Xiaocong Zhou","submitted_at":"2024-01-03T13:19:14Z","abstract_excerpt":"Multi-modal (vision-language) models, such as CLIP, are replacing traditional supervised pre-training models (e.g., ImageNet-based pre-training) as the new generation of visual foundation models. These models with robust and aligned semantic representations learned from billions of internet image-text pairs and can be applied to various downstream tasks in a zero-shot manner. However, in some fine-grained domains like medical imaging and remote sensing, the performance of multi-modal foundation models often leaves much to be desired. Consequently, many researchers have begun to explore few-sho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.01736","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/2401.01736/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":"2401.01736","created_at":"2026-07-05T07:30:07.848540+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.01736v2","created_at":"2026-07-05T07:30:07.848540+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.01736","created_at":"2026-07-05T07:30:07.848540+00:00"},{"alias_kind":"pith_short_12","alias_value":"AHYK2ET5ZA7I","created_at":"2026-07-05T07:30:07.848540+00:00"},{"alias_kind":"pith_short_16","alias_value":"AHYK2ET5ZA7I4F2S","created_at":"2026-07-05T07:30:07.848540+00:00"},{"alias_kind":"pith_short_8","alias_value":"AHYK2ET5","created_at":"2026-07-05T07:30:07.848540+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.03950","citing_title":"LR0.FM: Low-Res Benchmark and Improving Robustness for Zero-Shot Classification in Foundation Models","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AHYK2ET5ZA7I4F2SHYQ47LHQCC","json":"https://pith.science/pith/AHYK2ET5ZA7I4F2SHYQ47LHQCC.json","graph_json":"https://pith.science/api/pith-number/AHYK2ET5ZA7I4F2SHYQ47LHQCC/graph.json","events_json":"https://pith.science/api/pith-number/AHYK2ET5ZA7I4F2SHYQ47LHQCC/events.json","paper":"https://pith.science/paper/AHYK2ET5"},"agent_actions":{"view_html":"https://pith.science/pith/AHYK2ET5ZA7I4F2SHYQ47LHQCC","download_json":"https://pith.science/pith/AHYK2ET5ZA7I4F2SHYQ47LHQCC.json","view_paper":"https://pith.science/paper/AHYK2ET5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.01736&json=true","fetch_graph":"https://pith.science/api/pith-number/AHYK2ET5ZA7I4F2SHYQ47LHQCC/graph.json","fetch_events":"https://pith.science/api/pith-number/AHYK2ET5ZA7I4F2SHYQ47LHQCC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AHYK2ET5ZA7I4F2SHYQ47LHQCC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AHYK2ET5ZA7I4F2SHYQ47LHQCC/action/storage_attestation","attest_author":"https://pith.science/pith/AHYK2ET5ZA7I4F2SHYQ47LHQCC/action/author_attestation","sign_citation":"https://pith.science/pith/AHYK2ET5ZA7I4F2SHYQ47LHQCC/action/citation_signature","submit_replication":"https://pith.science/pith/AHYK2ET5ZA7I4F2SHYQ47LHQCC/action/replication_record"}},"created_at":"2026-07-05T07:30:07.848540+00:00","updated_at":"2026-07-05T07:30:07.848540+00:00"}