{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2ZF2N4K5G3MUVOGDTQDHLR7T3C","short_pith_number":"pith:2ZF2N4K5","schema_version":"1.0","canonical_sha256":"d64ba6f15d36d94ab8c39c0675c7f3d8ba34950906bbe7c89c13329c413b2748","source":{"kind":"arxiv","id":"2605.21861","version":1},"attestation_state":"computed","paper":{"title":"Learning Emergent Modular Representations in Multi-modality Medical Vision Foundation Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenyu You, Shuo Li, Yuting He","submitted_at":"2026-05-21T01:17:13Z","abstract_excerpt":"Multi-modality medical vision (MV) foundation models (FM) are fundamentally challenged by pronounced Non-IID feature statistics across heterogeneous imaging modalities. Monolithic self-supervised optimization on such data induces conflicting gradients, driving representations to collapse toward modality-dominant shortcuts. This work reframes this failure as an imbalance between specialization and coordination in emergent modularity, and proposes Director-Experts (DEX), a modular network that explicitly regulates these dynamics in stacked modules. Each DEX module comprises a pool of experts, dy"},"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":"2605.21861","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T01:17:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a42b63913740b2778c8acc67a070e5c1fa01f755e7f5afca8428e306e319ce21","abstract_canon_sha256":"933cc1a6b8b79329980bed07242a2a0c67a4ff7983275c8ec7e1d1d902203747"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:11.846639Z","signature_b64":"ENghWbgjvtkEkYYI026BzGspoAsz9WYSM8GLIlT49JKjSO50ZMaRwctJBVi8Pm5BJcbmu7lBz+Z/TKUzmUfvBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d64ba6f15d36d94ab8c39c0675c7f3d8ba34950906bbe7c89c13329c413b2748","last_reissued_at":"2026-05-22T01:04:11.845700Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:11.845700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Emergent Modular Representations in Multi-modality Medical Vision Foundation Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenyu You, Shuo Li, Yuting He","submitted_at":"2026-05-21T01:17:13Z","abstract_excerpt":"Multi-modality medical vision (MV) foundation models (FM) are fundamentally challenged by pronounced Non-IID feature statistics across heterogeneous imaging modalities. Monolithic self-supervised optimization on such data induces conflicting gradients, driving representations to collapse toward modality-dominant shortcuts. This work reframes this failure as an imbalance between specialization and coordination in emergent modularity, and proposes Director-Experts (DEX), a modular network that explicitly regulates these dynamics in stacked modules. Each DEX module comprises a pool of experts, dy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21861","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/2605.21861/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":"2605.21861","created_at":"2026-05-22T01:04:11.845888+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21861v1","created_at":"2026-05-22T01:04:11.845888+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21861","created_at":"2026-05-22T01:04:11.845888+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ZF2N4K5G3MU","created_at":"2026-05-22T01:04:11.845888+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ZF2N4K5G3MUVOGD","created_at":"2026-05-22T01:04:11.845888+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ZF2N4K5","created_at":"2026-05-22T01:04:11.845888+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/2ZF2N4K5G3MUVOGDTQDHLR7T3C","json":"https://pith.science/pith/2ZF2N4K5G3MUVOGDTQDHLR7T3C.json","graph_json":"https://pith.science/api/pith-number/2ZF2N4K5G3MUVOGDTQDHLR7T3C/graph.json","events_json":"https://pith.science/api/pith-number/2ZF2N4K5G3MUVOGDTQDHLR7T3C/events.json","paper":"https://pith.science/paper/2ZF2N4K5"},"agent_actions":{"view_html":"https://pith.science/pith/2ZF2N4K5G3MUVOGDTQDHLR7T3C","download_json":"https://pith.science/pith/2ZF2N4K5G3MUVOGDTQDHLR7T3C.json","view_paper":"https://pith.science/paper/2ZF2N4K5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21861&json=true","fetch_graph":"https://pith.science/api/pith-number/2ZF2N4K5G3MUVOGDTQDHLR7T3C/graph.json","fetch_events":"https://pith.science/api/pith-number/2ZF2N4K5G3MUVOGDTQDHLR7T3C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ZF2N4K5G3MUVOGDTQDHLR7T3C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ZF2N4K5G3MUVOGDTQDHLR7T3C/action/storage_attestation","attest_author":"https://pith.science/pith/2ZF2N4K5G3MUVOGDTQDHLR7T3C/action/author_attestation","sign_citation":"https://pith.science/pith/2ZF2N4K5G3MUVOGDTQDHLR7T3C/action/citation_signature","submit_replication":"https://pith.science/pith/2ZF2N4K5G3MUVOGDTQDHLR7T3C/action/replication_record"}},"created_at":"2026-05-22T01:04:11.845888+00:00","updated_at":"2026-05-22T01:04:11.845888+00:00"}