{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:E3NDSGFQCI3UFSJ3K7AL2IFDUN","short_pith_number":"pith:E3NDSGFQ","schema_version":"1.0","canonical_sha256":"26da3918b0123742c93b57c0bd20a3a360514db50a1ea20bf2d6db6c9bf4263b","source":{"kind":"arxiv","id":"2409.19540","version":1},"attestation_state":"computed","paper":{"title":"LoRKD: Low-Rank Knowledge Decomposition for Medical Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haolin Li, Jiangchao Yao, Siyuan Du, Weidi Xie, Yanfeng Wang, Ya Zhang, Yuhang Zhou, Ziheng Zhao","submitted_at":"2024-09-29T03:56:21Z","abstract_excerpt":"The widespread adoption of large-scale pre-training techniques has significantly advanced the development of medical foundation models, enabling them to serve as versatile tools across a broad range of medical tasks. However, despite their strong generalization capabilities, medical foundation models pre-trained on large-scale datasets tend to suffer from domain gaps between heterogeneous data, leading to suboptimal performance on specific tasks compared to specialist models, as evidenced by previous studies. In this paper, we explore a new perspective called \"Knowledge Decomposition\" to impro"},"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":"2409.19540","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-29T03:56:21Z","cross_cats_sorted":[],"title_canon_sha256":"ba241735ff0c7b4b3bfd0e75592e23b570fb981f4d7101807583521b9293295b","abstract_canon_sha256":"d750073c845e4c9781a43334cfc2cfac42a09ffd4ccbb08a8b190a676f568856"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:12.930261Z","signature_b64":"sETPeK0qtfz8+PorPZVYMEkQ/e7F/y29cG1NKSbsFMQOmdcdSOi+WowQv+FxfwVzCqX9N8W+izCEFauXogQrBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26da3918b0123742c93b57c0bd20a3a360514db50a1ea20bf2d6db6c9bf4263b","last_reissued_at":"2026-07-05T09:23:12.929756Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:12.929756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LoRKD: Low-Rank Knowledge Decomposition for Medical Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haolin Li, Jiangchao Yao, Siyuan Du, Weidi Xie, Yanfeng Wang, Ya Zhang, Yuhang Zhou, Ziheng Zhao","submitted_at":"2024-09-29T03:56:21Z","abstract_excerpt":"The widespread adoption of large-scale pre-training techniques has significantly advanced the development of medical foundation models, enabling them to serve as versatile tools across a broad range of medical tasks. However, despite their strong generalization capabilities, medical foundation models pre-trained on large-scale datasets tend to suffer from domain gaps between heterogeneous data, leading to suboptimal performance on specific tasks compared to specialist models, as evidenced by previous studies. In this paper, we explore a new perspective called \"Knowledge Decomposition\" to impro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19540","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/2409.19540/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":"2409.19540","created_at":"2026-07-05T09:23:12.929818+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.19540v1","created_at":"2026-07-05T09:23:12.929818+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19540","created_at":"2026-07-05T09:23:12.929818+00:00"},{"alias_kind":"pith_short_12","alias_value":"E3NDSGFQCI3U","created_at":"2026-07-05T09:23:12.929818+00:00"},{"alias_kind":"pith_short_16","alias_value":"E3NDSGFQCI3UFSJ3","created_at":"2026-07-05T09:23:12.929818+00:00"},{"alias_kind":"pith_short_8","alias_value":"E3NDSGFQ","created_at":"2026-07-05T09:23:12.929818+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04447","citing_title":"Deep Reprogramming Distillation for Medical Foundation Models","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E3NDSGFQCI3UFSJ3K7AL2IFDUN","json":"https://pith.science/pith/E3NDSGFQCI3UFSJ3K7AL2IFDUN.json","graph_json":"https://pith.science/api/pith-number/E3NDSGFQCI3UFSJ3K7AL2IFDUN/graph.json","events_json":"https://pith.science/api/pith-number/E3NDSGFQCI3UFSJ3K7AL2IFDUN/events.json","paper":"https://pith.science/paper/E3NDSGFQ"},"agent_actions":{"view_html":"https://pith.science/pith/E3NDSGFQCI3UFSJ3K7AL2IFDUN","download_json":"https://pith.science/pith/E3NDSGFQCI3UFSJ3K7AL2IFDUN.json","view_paper":"https://pith.science/paper/E3NDSGFQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.19540&json=true","fetch_graph":"https://pith.science/api/pith-number/E3NDSGFQCI3UFSJ3K7AL2IFDUN/graph.json","fetch_events":"https://pith.science/api/pith-number/E3NDSGFQCI3UFSJ3K7AL2IFDUN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E3NDSGFQCI3UFSJ3K7AL2IFDUN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E3NDSGFQCI3UFSJ3K7AL2IFDUN/action/storage_attestation","attest_author":"https://pith.science/pith/E3NDSGFQCI3UFSJ3K7AL2IFDUN/action/author_attestation","sign_citation":"https://pith.science/pith/E3NDSGFQCI3UFSJ3K7AL2IFDUN/action/citation_signature","submit_replication":"https://pith.science/pith/E3NDSGFQCI3UFSJ3K7AL2IFDUN/action/replication_record"}},"created_at":"2026-07-05T09:23:12.929818+00:00","updated_at":"2026-07-05T09:23:12.929818+00:00"}