{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6NIYHSFPTGYZHAA3HLOGGQMPH2","short_pith_number":"pith:6NIYHSFP","schema_version":"1.0","canonical_sha256":"f35183c8af99b193801b3adc63418f3ea2823c822bd84608c7c250c7f3c0f642","source":{"kind":"arxiv","id":"2503.00802","version":1},"attestation_state":"computed","paper":{"title":"MFM-DA: Instance-Aware Adaptor and Hierarchical Alignment for Efficient Domain Adaptation in Medical Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Furong Li, Hongtao Wu, Jia-Xuan Jiang, Wenhui Lei, Xiaofan Zhang, Yifeng Wu, Yining Xie, Zhong Wang","submitted_at":"2025-03-02T08:54:33Z","abstract_excerpt":"Medical Foundation Models (MFMs), trained on large-scale datasets, have demonstrated superior performance across various tasks. However, these models still struggle with domain gaps in practical applications. Specifically, even after fine-tuning on source-domain data, task-adapted foundation models often perform poorly in the target domain. To address this challenge, we propose a few-shot unsupervised domain adaptation (UDA) framework for MFMs, named MFM-DA, which only leverages a limited number of unlabeled target-domain images. Our approach begins by training a Denoising Diffusion Probabilis"},"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":"2503.00802","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-02T08:54:33Z","cross_cats_sorted":[],"title_canon_sha256":"84315396984b4951093d28259e7c85af0fc566b723c9a1908cc0e138ceda139f","abstract_canon_sha256":"c1587ad44821e1b73540f18f1f7e18e169fa108f3f8dc4965c1b06288dc40728"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:30.000084Z","signature_b64":"ulfu71QpDMxCpKVc1tIv1DOxOu6Ap4Q0ydF6jxqRauy6Ku4RjXip0TRduiNQamGjkLDtjMHe/djVgC3rf1ZIDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f35183c8af99b193801b3adc63418f3ea2823c822bd84608c7c250c7f3c0f642","last_reissued_at":"2026-07-05T10:22:29.999595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:29.999595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MFM-DA: Instance-Aware Adaptor and Hierarchical Alignment for Efficient Domain Adaptation in Medical Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Furong Li, Hongtao Wu, Jia-Xuan Jiang, Wenhui Lei, Xiaofan Zhang, Yifeng Wu, Yining Xie, Zhong Wang","submitted_at":"2025-03-02T08:54:33Z","abstract_excerpt":"Medical Foundation Models (MFMs), trained on large-scale datasets, have demonstrated superior performance across various tasks. However, these models still struggle with domain gaps in practical applications. Specifically, even after fine-tuning on source-domain data, task-adapted foundation models often perform poorly in the target domain. To address this challenge, we propose a few-shot unsupervised domain adaptation (UDA) framework for MFMs, named MFM-DA, which only leverages a limited number of unlabeled target-domain images. Our approach begins by training a Denoising Diffusion Probabilis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00802","kind":"arxiv","version":1},"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/2503.00802/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":"2503.00802","created_at":"2026-07-05T10:22:29.999652+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.00802v1","created_at":"2026-07-05T10:22:29.999652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00802","created_at":"2026-07-05T10:22:29.999652+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NIYHSFPTGYZ","created_at":"2026-07-05T10:22:29.999652+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NIYHSFPTGYZHAA3","created_at":"2026-07-05T10:22:29.999652+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NIYHSFP","created_at":"2026-07-05T10:22:29.999652+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.08340","citing_title":"Single Domain Generalization for Multimodal Cross-Cancer Prognosis via Dirac Rebalancer and Distribution Entanglement","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6NIYHSFPTGYZHAA3HLOGGQMPH2","json":"https://pith.science/pith/6NIYHSFPTGYZHAA3HLOGGQMPH2.json","graph_json":"https://pith.science/api/pith-number/6NIYHSFPTGYZHAA3HLOGGQMPH2/graph.json","events_json":"https://pith.science/api/pith-number/6NIYHSFPTGYZHAA3HLOGGQMPH2/events.json","paper":"https://pith.science/paper/6NIYHSFP"},"agent_actions":{"view_html":"https://pith.science/pith/6NIYHSFPTGYZHAA3HLOGGQMPH2","download_json":"https://pith.science/pith/6NIYHSFPTGYZHAA3HLOGGQMPH2.json","view_paper":"https://pith.science/paper/6NIYHSFP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.00802&json=true","fetch_graph":"https://pith.science/api/pith-number/6NIYHSFPTGYZHAA3HLOGGQMPH2/graph.json","fetch_events":"https://pith.science/api/pith-number/6NIYHSFPTGYZHAA3HLOGGQMPH2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NIYHSFPTGYZHAA3HLOGGQMPH2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NIYHSFPTGYZHAA3HLOGGQMPH2/action/storage_attestation","attest_author":"https://pith.science/pith/6NIYHSFPTGYZHAA3HLOGGQMPH2/action/author_attestation","sign_citation":"https://pith.science/pith/6NIYHSFPTGYZHAA3HLOGGQMPH2/action/citation_signature","submit_replication":"https://pith.science/pith/6NIYHSFPTGYZHAA3HLOGGQMPH2/action/replication_record"}},"created_at":"2026-07-05T10:22:29.999652+00:00","updated_at":"2026-07-05T10:22:29.999652+00:00"}