{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AHYK2ET5ZA7I4F2SHYQ47LHQCC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0cbd6a8609b77ef65e90a5f66295176bd2c639fe49e79dc8288d512ae0221c03","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-03T13:19:14Z","title_canon_sha256":"f511a7e91543ec5ca42fec965a715b0f36bb34fb4ed8e66b13727164da1db6bd"},"schema_version":"1.0","source":{"id":"2401.01736","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.01736","created_at":"2026-07-05T07:30:07Z"},{"alias_kind":"arxiv_version","alias_value":"2401.01736v2","created_at":"2026-07-05T07:30:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.01736","created_at":"2026-07-05T07:30:07Z"},{"alias_kind":"pith_short_12","alias_value":"AHYK2ET5ZA7I","created_at":"2026-07-05T07:30:07Z"},{"alias_kind":"pith_short_16","alias_value":"AHYK2ET5ZA7I4F2S","created_at":"2026-07-05T07:30:07Z"},{"alias_kind":"pith_short_8","alias_value":"AHYK2ET5","created_at":"2026-07-05T07:30:07Z"}],"graph_snapshots":[{"event_id":"sha256:91704c9233f97ec0e20b818fcbfc6086529a1b6c90a15b21fe1609900866b676","target":"graph","created_at":"2026-07-05T07:30:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2401.01736/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Delong Chen, Fan Liu, Tianshu Zhang, Wenwen Cai, Wenwen Dai, Xiaocong Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-03T13:19:14Z","title":"Few-shot Adaptation of Multi-modal Foundation Models: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.01736","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:91c9727311e4215e69b33baa0878020df75fc2e1b5fa019d8693b752e76f62c8","target":"record","created_at":"2026-07-05T07:30:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0cbd6a8609b77ef65e90a5f66295176bd2c639fe49e79dc8288d512ae0221c03","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-03T13:19:14Z","title_canon_sha256":"f511a7e91543ec5ca42fec965a715b0f36bb34fb4ed8e66b13727164da1db6bd"},"schema_version":"1.0","source":{"id":"2401.01736","kind":"arxiv","version":2}},"canonical_sha256":"01f0ad127dc83e8e17523e21cfacf0109e134d2e96e11d2c03f202d348eae573","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01f0ad127dc83e8e17523e21cfacf0109e134d2e96e11d2c03f202d348eae573","first_computed_at":"2026-07-05T07:30:07.848482Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:30:07.848482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GqBzEOftsMGuxGfxLVzVfFbHybf3rs2tCWIibDBmtaExQLbeqg7Fu1CbbLzdPv7lH9bW2u978bOaghs7AaptDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:30:07.848875Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.01736","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:91c9727311e4215e69b33baa0878020df75fc2e1b5fa019d8693b752e76f62c8","sha256:91704c9233f97ec0e20b818fcbfc6086529a1b6c90a15b21fe1609900866b676"],"state_sha256":"290e7943ec820d4953f27d687b89bf094faf754506a1928d3ae8b27f602192cf"}