{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PA347VRYHRVZSRTAMDYO6NORYY","short_pith_number":"pith:PA347VRY","schema_version":"1.0","canonical_sha256":"7837cfd6383c6b99466060f0ef35d1c62678e22f6299c1b91f6b94e8310334a5","source":{"kind":"arxiv","id":"2405.12217","version":2},"attestation_state":"computed","paper":{"title":"Adapting Large Multimodal Models to Distribution Shifts: The Role of In-Context Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Biwei Huang, Guanglin Zhou, Liming Zhu, Lina Yao, Salman Khan, Shiming Chen, Xin Gao, Zhongyi Han","submitted_at":"2024-05-20T17:59:21Z","abstract_excerpt":"Recent studies indicate that large multimodal models (LMMs) potentially act as general-purpose assistants and are highly robust against different distributions. Despite this, domain-specific adaptation is still necessary particularly in specialized areas like healthcare. Due to the impracticality of fine-tuning LMMs given their vast parameter space, this work investigates in-context learning (ICL) as an effective alternative for enhancing LMMs' adaptability. Our study addresses this by evaluating an unsupervised ICL method which selects in-context examples through a nearest example search base"},"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":"2405.12217","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-20T17:59:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9b408c333cce498df7915212b901d22c36c9ac04121678fd44e9e68b3d32af0c","abstract_canon_sha256":"64ec268d107f2906ff047605abede65144f99fc82962ded0990094ef7fc59cae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:23.438745Z","signature_b64":"te0u6aEhNCPqCiY6tLsilPcgQGi6eynztH/z0h1vVlDFUECEzTI62SOwoWVW/ZoqvLJ+icUULkJNz5lzx8nFAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7837cfd6383c6b99466060f0ef35d1c62678e22f6299c1b91f6b94e8310334a5","last_reissued_at":"2026-07-05T09:20:23.438231Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:23.438231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adapting Large Multimodal Models to Distribution Shifts: The Role of In-Context Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Biwei Huang, Guanglin Zhou, Liming Zhu, Lina Yao, Salman Khan, Shiming Chen, Xin Gao, Zhongyi Han","submitted_at":"2024-05-20T17:59:21Z","abstract_excerpt":"Recent studies indicate that large multimodal models (LMMs) potentially act as general-purpose assistants and are highly robust against different distributions. Despite this, domain-specific adaptation is still necessary particularly in specialized areas like healthcare. Due to the impracticality of fine-tuning LMMs given their vast parameter space, this work investigates in-context learning (ICL) as an effective alternative for enhancing LMMs' adaptability. Our study addresses this by evaluating an unsupervised ICL method which selects in-context examples through a nearest example search base"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.12217","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/2405.12217/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":"2405.12217","created_at":"2026-07-05T09:20:23.438301+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.12217v2","created_at":"2026-07-05T09:20:23.438301+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.12217","created_at":"2026-07-05T09:20:23.438301+00:00"},{"alias_kind":"pith_short_12","alias_value":"PA347VRYHRVZ","created_at":"2026-07-05T09:20:23.438301+00:00"},{"alias_kind":"pith_short_16","alias_value":"PA347VRYHRVZSRTA","created_at":"2026-07-05T09:20:23.438301+00:00"},{"alias_kind":"pith_short_8","alias_value":"PA347VRY","created_at":"2026-07-05T09:20:23.438301+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PA347VRYHRVZSRTAMDYO6NORYY","json":"https://pith.science/pith/PA347VRYHRVZSRTAMDYO6NORYY.json","graph_json":"https://pith.science/api/pith-number/PA347VRYHRVZSRTAMDYO6NORYY/graph.json","events_json":"https://pith.science/api/pith-number/PA347VRYHRVZSRTAMDYO6NORYY/events.json","paper":"https://pith.science/paper/PA347VRY"},"agent_actions":{"view_html":"https://pith.science/pith/PA347VRYHRVZSRTAMDYO6NORYY","download_json":"https://pith.science/pith/PA347VRYHRVZSRTAMDYO6NORYY.json","view_paper":"https://pith.science/paper/PA347VRY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.12217&json=true","fetch_graph":"https://pith.science/api/pith-number/PA347VRYHRVZSRTAMDYO6NORYY/graph.json","fetch_events":"https://pith.science/api/pith-number/PA347VRYHRVZSRTAMDYO6NORYY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PA347VRYHRVZSRTAMDYO6NORYY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PA347VRYHRVZSRTAMDYO6NORYY/action/storage_attestation","attest_author":"https://pith.science/pith/PA347VRYHRVZSRTAMDYO6NORYY/action/author_attestation","sign_citation":"https://pith.science/pith/PA347VRYHRVZSRTAMDYO6NORYY/action/citation_signature","submit_replication":"https://pith.science/pith/PA347VRYHRVZSRTAMDYO6NORYY/action/replication_record"}},"created_at":"2026-07-05T09:20:23.438301+00:00","updated_at":"2026-07-05T09:20:23.438301+00:00"}