{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VQBWHXFTTBEHUB7FZFU3LG42IY","short_pith_number":"pith:VQBWHXFT","schema_version":"1.0","canonical_sha256":"ac0363dcb398487a07e5c969b59b9a462a27622038c9cf98ac995ae1fea12f48","source":{"kind":"arxiv","id":"2509.06617","version":1},"attestation_state":"computed","paper":{"title":"MM-DINOv2: Adapting Foundation Models for Multi-Modal Medical Image Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Anke Meyer-Baese, Ayhan Can Erdur, Benedikt Wiestler, Daniel Rueckert, Daniel Scholz, Jan C. Peeken, Viktoria Ehm","submitted_at":"2025-09-08T12:34:15Z","abstract_excerpt":"Vision foundation models like DINOv2 demonstrate remarkable potential in medical imaging despite their origin in natural image domains. However, their design inherently works best for uni-modal image analysis, limiting their effectiveness for multi-modal imaging tasks that are common in many medical fields, such as neurology and oncology. While supervised models perform well in this setting, they fail to leverage unlabeled datasets and struggle with missing modalities, a frequent challenge in clinical settings. To bridge these gaps, we introduce MM-DINOv2, a novel and efficient framework that "},"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":"2509.06617","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2025-09-08T12:34:15Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"bcf89f5c15b6b9ceab89a090e96b1bafbc525957108e04fcd5c3c32ee2978e44","abstract_canon_sha256":"192349ea6c8de6043f3d3c5a478e4240040070a11bdd488f4d4b070c2bd15c76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:39.303060Z","signature_b64":"aYJXslqkh0WY4xA1mlY4D42gmMZyFzfld1bBsZ6Pj6kPOYoWkK8wpsMoxczxo+98KmgPZSWcFvdGXtQr7rV0Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac0363dcb398487a07e5c969b59b9a462a27622038c9cf98ac995ae1fea12f48","last_reissued_at":"2026-07-05T12:06:39.302622Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:39.302622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MM-DINOv2: Adapting Foundation Models for Multi-Modal Medical Image Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Anke Meyer-Baese, Ayhan Can Erdur, Benedikt Wiestler, Daniel Rueckert, Daniel Scholz, Jan C. Peeken, Viktoria Ehm","submitted_at":"2025-09-08T12:34:15Z","abstract_excerpt":"Vision foundation models like DINOv2 demonstrate remarkable potential in medical imaging despite their origin in natural image domains. However, their design inherently works best for uni-modal image analysis, limiting their effectiveness for multi-modal imaging tasks that are common in many medical fields, such as neurology and oncology. While supervised models perform well in this setting, they fail to leverage unlabeled datasets and struggle with missing modalities, a frequent challenge in clinical settings. To bridge these gaps, we introduce MM-DINOv2, a novel and efficient framework that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06617","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/2509.06617/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":"2509.06617","created_at":"2026-07-05T12:06:39.302680+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.06617v1","created_at":"2026-07-05T12:06:39.302680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06617","created_at":"2026-07-05T12:06:39.302680+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQBWHXFTTBEH","created_at":"2026-07-05T12:06:39.302680+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQBWHXFTTBEHUB7F","created_at":"2026-07-05T12:06:39.302680+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQBWHXFT","created_at":"2026-07-05T12:06:39.302680+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.13300","citing_title":"Improving Medical Image Generative Models with Fr\\'echet Distance Loss","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VQBWHXFTTBEHUB7FZFU3LG42IY","json":"https://pith.science/pith/VQBWHXFTTBEHUB7FZFU3LG42IY.json","graph_json":"https://pith.science/api/pith-number/VQBWHXFTTBEHUB7FZFU3LG42IY/graph.json","events_json":"https://pith.science/api/pith-number/VQBWHXFTTBEHUB7FZFU3LG42IY/events.json","paper":"https://pith.science/paper/VQBWHXFT"},"agent_actions":{"view_html":"https://pith.science/pith/VQBWHXFTTBEHUB7FZFU3LG42IY","download_json":"https://pith.science/pith/VQBWHXFTTBEHUB7FZFU3LG42IY.json","view_paper":"https://pith.science/paper/VQBWHXFT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.06617&json=true","fetch_graph":"https://pith.science/api/pith-number/VQBWHXFTTBEHUB7FZFU3LG42IY/graph.json","fetch_events":"https://pith.science/api/pith-number/VQBWHXFTTBEHUB7FZFU3LG42IY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQBWHXFTTBEHUB7FZFU3LG42IY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQBWHXFTTBEHUB7FZFU3LG42IY/action/storage_attestation","attest_author":"https://pith.science/pith/VQBWHXFTTBEHUB7FZFU3LG42IY/action/author_attestation","sign_citation":"https://pith.science/pith/VQBWHXFTTBEHUB7FZFU3LG42IY/action/citation_signature","submit_replication":"https://pith.science/pith/VQBWHXFTTBEHUB7FZFU3LG42IY/action/replication_record"}},"created_at":"2026-07-05T12:06:39.302680+00:00","updated_at":"2026-07-05T12:06:39.302680+00:00"}