{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AHYK2ET5ZA7I4F2SHYQ47LHQCC","short_pith_number":"pith:AHYK2ET5","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"},"canonical_sha256":"01f0ad127dc83e8e17523e21cfacf0109e134d2e96e11d2c03f202d348eae573","source":{"kind":"arxiv","id":"2401.01736","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AHYK2ET5ZA7I4F2SHYQ47LHQCC","target":"record","payload":{"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"},"canonical_sha256":"01f0ad127dc83e8e17523e21cfacf0109e134d2e96e11d2c03f202d348eae573","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"},"source_kind":"arxiv","source_id":"2401.01736","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:30:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gEGVdaNK8pQZPTyA1aCY4kuDTxD+vUzE4REx7WN+4FTKiOWVcnOVbZ97TwqqWX57P1PckKY1A7QX8EpW3mzCCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:31:31.782977Z"},"content_sha256":"91c9727311e4215e69b33baa0878020df75fc2e1b5fa019d8693b752e76f62c8","schema_version":"1.0","event_id":"sha256:91c9727311e4215e69b33baa0878020df75fc2e1b5fa019d8693b752e76f62c8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AHYK2ET5ZA7I4F2SHYQ47LHQCC","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:30:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T6oRlrkLboZuY752mZhVuAk2j3+PxifUwEWrs3akg8h8umqOKZVbV46p/v/JYw8PDBj5BKZrk4wq6uWhXcoWAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:31:31.783490Z"},"content_sha256":"91704c9233f97ec0e20b818fcbfc6086529a1b6c90a15b21fe1609900866b676","schema_version":"1.0","event_id":"sha256:91704c9233f97ec0e20b818fcbfc6086529a1b6c90a15b21fe1609900866b676"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AHYK2ET5ZA7I4F2SHYQ47LHQCC/bundle.json","state_url":"https://pith.science/pith/AHYK2ET5ZA7I4F2SHYQ47LHQCC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AHYK2ET5ZA7I4F2SHYQ47LHQCC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T22:31:31Z","links":{"resolver":"https://pith.science/pith/AHYK2ET5ZA7I4F2SHYQ47LHQCC","bundle":"https://pith.science/pith/AHYK2ET5ZA7I4F2SHYQ47LHQCC/bundle.json","state":"https://pith.science/pith/AHYK2ET5ZA7I4F2SHYQ47LHQCC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AHYK2ET5ZA7I4F2SHYQ47LHQCC/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f26UEhvkXkYhx4xcS0dWH0tvl37KMzivbsdgJIsZ5MtAYdZDxqilMJ16msc7FD7FeNEmN4s6211GIBEWggfKBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T22:31:31.788037Z","bundle_sha256":"8fa954be3a447850bc6956753da228a26a2d5e6f5fcab22ce3e89fa9f804af63"}}