{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UHZY3X2NEPHCKOWCK3QAWKAUQ6","short_pith_number":"pith:UHZY3X2N","schema_version":"1.0","canonical_sha256":"a1f38ddf4d23ce253ac256e00b281487855ae97daeac3159322cb45e91b624f8","source":{"kind":"arxiv","id":"2506.08356","version":2},"attestation_state":"computed","paper":{"title":"MedMoE: Modality-Specialized Mixture of Experts for Medical Vision-Language Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew J Feola, Gabriela Sanchez-Rodriguez, Jing Li, Lingchao Mao, Shivang Chopra, Zsolt Kira","submitted_at":"2025-06-10T02:14:15Z","abstract_excerpt":"Different medical imaging modalities capture diagnostic information at varying spatial resolutions, from coarse global patterns to fine-grained localized structures. However, most existing vision-language frameworks in the medical domain apply a uniform strategy for local feature extraction, overlooking the modality-specific demands. In this work, we present MedMoE, a modular and extensible vision-language processing framework that dynamically adapts visual representation based on the diagnostic context. MedMoE incorporates a Mixture-of-Experts (MoE) module conditioned on the report type, whic"},"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":"2506.08356","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-10T02:14:15Z","cross_cats_sorted":[],"title_canon_sha256":"c6368c9c084f48facd072f1b12f8a898c50ff1dc9c4e838c596755fd066657ad","abstract_canon_sha256":"c090129b2eecec7b53d5da41aff9ff98b8742de5b37cf0383931db7075a2a36e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:53.759803Z","signature_b64":"OPvDGbGC2MVATTdWQaOekkNLglPgtWLLcIAU7RHdkmUTS1tyig5nlwM/bC/jxAxbwcB5ICc191VLfST9LrejDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1f38ddf4d23ce253ac256e00b281487855ae97daeac3159322cb45e91b624f8","last_reissued_at":"2026-07-05T11:19:53.759348Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:53.759348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedMoE: Modality-Specialized Mixture of Experts for Medical Vision-Language Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew J Feola, Gabriela Sanchez-Rodriguez, Jing Li, Lingchao Mao, Shivang Chopra, Zsolt Kira","submitted_at":"2025-06-10T02:14:15Z","abstract_excerpt":"Different medical imaging modalities capture diagnostic information at varying spatial resolutions, from coarse global patterns to fine-grained localized structures. However, most existing vision-language frameworks in the medical domain apply a uniform strategy for local feature extraction, overlooking the modality-specific demands. In this work, we present MedMoE, a modular and extensible vision-language processing framework that dynamically adapts visual representation based on the diagnostic context. MedMoE incorporates a Mixture-of-Experts (MoE) module conditioned on the report type, whic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08356","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/2506.08356/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":"2506.08356","created_at":"2026-07-05T11:19:53.759412+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.08356v2","created_at":"2026-07-05T11:19:53.759412+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08356","created_at":"2026-07-05T11:19:53.759412+00:00"},{"alias_kind":"pith_short_12","alias_value":"UHZY3X2NEPHC","created_at":"2026-07-05T11:19:53.759412+00:00"},{"alias_kind":"pith_short_16","alias_value":"UHZY3X2NEPHCKOWC","created_at":"2026-07-05T11:19:53.759412+00:00"},{"alias_kind":"pith_short_8","alias_value":"UHZY3X2N","created_at":"2026-07-05T11:19:53.759412+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27431","citing_title":"Tackling Multimodal Learning Challenges with Mixture-of-Expert: A Survey","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21861","citing_title":"Learning Emergent Modular Representations in Multi-modality Medical Vision Foundation Models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26283","citing_title":"MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26283","citing_title":"MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08936","citing_title":"M-IDoL: Information Decomposition for Modality-Specific and Diverse Representation Learning in Medical Foundation Model","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UHZY3X2NEPHCKOWCK3QAWKAUQ6","json":"https://pith.science/pith/UHZY3X2NEPHCKOWCK3QAWKAUQ6.json","graph_json":"https://pith.science/api/pith-number/UHZY3X2NEPHCKOWCK3QAWKAUQ6/graph.json","events_json":"https://pith.science/api/pith-number/UHZY3X2NEPHCKOWCK3QAWKAUQ6/events.json","paper":"https://pith.science/paper/UHZY3X2N"},"agent_actions":{"view_html":"https://pith.science/pith/UHZY3X2NEPHCKOWCK3QAWKAUQ6","download_json":"https://pith.science/pith/UHZY3X2NEPHCKOWCK3QAWKAUQ6.json","view_paper":"https://pith.science/paper/UHZY3X2N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.08356&json=true","fetch_graph":"https://pith.science/api/pith-number/UHZY3X2NEPHCKOWCK3QAWKAUQ6/graph.json","fetch_events":"https://pith.science/api/pith-number/UHZY3X2NEPHCKOWCK3QAWKAUQ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UHZY3X2NEPHCKOWCK3QAWKAUQ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UHZY3X2NEPHCKOWCK3QAWKAUQ6/action/storage_attestation","attest_author":"https://pith.science/pith/UHZY3X2NEPHCKOWCK3QAWKAUQ6/action/author_attestation","sign_citation":"https://pith.science/pith/UHZY3X2NEPHCKOWCK3QAWKAUQ6/action/citation_signature","submit_replication":"https://pith.science/pith/UHZY3X2NEPHCKOWCK3QAWKAUQ6/action/replication_record"}},"created_at":"2026-07-05T11:19:53.759412+00:00","updated_at":"2026-07-05T11:19:53.759412+00:00"}