{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AWHYVVJC4SBMYRDPZ2JNAC2W2U","short_pith_number":"pith:AWHYVVJC","schema_version":"1.0","canonical_sha256":"058f8ad522e482cc446fce92d00b56d51dd5601f283983db675cbd26270b8aa1","source":{"kind":"arxiv","id":"2607.06633","version":1},"attestation_state":"computed","paper":{"title":"ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aavash Chhetri, Bibek Niroula, Binod Bhattarai, Eduard Vazquez, Loris Bazzani, Prashnna Gyawali, Yash Raj Shrestha","submitted_at":"2026-07-07T13:43:20Z","abstract_excerpt":"In this paper, we address the problem of multimodal federated learning with missing modality. Existing methods utilize an additional public dataset or perform naive feature synthesis that is based solely on the available modality. To address these limitations, we propose ProMoE-FL, a Prototype-conditioned Mixture-of-Experts framework for robust missing-modality feature synthesis in multimodal federated learning. ProMoE-FL builds a global client-aware prototype bank that captures clinically meaningful modality priors across institutions. Our Mixture of Experts is conditioned on these prototypes"},"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":"2607.06633","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-07T13:43:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"86b2839a0e7d69abdc6781fd2b13cc62775829412522c19f1f2cb0abbbb3041c","abstract_canon_sha256":"899ed8a739e7d7ed93bd72da91dc7d3c00857567af29701111e5f6f61a8305a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T00:19:21.149497Z","signature_b64":"5TX0kO7fJMwokOCFIEJZljLpZlIqWfxOyoa3W93OdAsFCXGzv/UKrfuEb8gpAoRGtbHIXSQZ834Jhityr4zYDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"058f8ad522e482cc446fce92d00b56d51dd5601f283983db675cbd26270b8aa1","last_reissued_at":"2026-07-09T00:19:21.149010Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T00:19:21.149010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aavash Chhetri, Bibek Niroula, Binod Bhattarai, Eduard Vazquez, Loris Bazzani, Prashnna Gyawali, Yash Raj Shrestha","submitted_at":"2026-07-07T13:43:20Z","abstract_excerpt":"In this paper, we address the problem of multimodal federated learning with missing modality. Existing methods utilize an additional public dataset or perform naive feature synthesis that is based solely on the available modality. To address these limitations, we propose ProMoE-FL, a Prototype-conditioned Mixture-of-Experts framework for robust missing-modality feature synthesis in multimodal federated learning. ProMoE-FL builds a global client-aware prototype bank that captures clinically meaningful modality priors across institutions. Our Mixture of Experts is conditioned on these prototypes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06633","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/2607.06633/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":"2607.06633","created_at":"2026-07-09T00:19:21.149077+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.06633v1","created_at":"2026-07-09T00:19:21.149077+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06633","created_at":"2026-07-09T00:19:21.149077+00:00"},{"alias_kind":"pith_short_12","alias_value":"AWHYVVJC4SBM","created_at":"2026-07-09T00:19:21.149077+00:00"},{"alias_kind":"pith_short_16","alias_value":"AWHYVVJC4SBMYRDP","created_at":"2026-07-09T00:19:21.149077+00:00"},{"alias_kind":"pith_short_8","alias_value":"AWHYVVJC","created_at":"2026-07-09T00:19:21.149077+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/AWHYVVJC4SBMYRDPZ2JNAC2W2U","json":"https://pith.science/pith/AWHYVVJC4SBMYRDPZ2JNAC2W2U.json","graph_json":"https://pith.science/api/pith-number/AWHYVVJC4SBMYRDPZ2JNAC2W2U/graph.json","events_json":"https://pith.science/api/pith-number/AWHYVVJC4SBMYRDPZ2JNAC2W2U/events.json","paper":"https://pith.science/paper/AWHYVVJC"},"agent_actions":{"view_html":"https://pith.science/pith/AWHYVVJC4SBMYRDPZ2JNAC2W2U","download_json":"https://pith.science/pith/AWHYVVJC4SBMYRDPZ2JNAC2W2U.json","view_paper":"https://pith.science/paper/AWHYVVJC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.06633&json=true","fetch_graph":"https://pith.science/api/pith-number/AWHYVVJC4SBMYRDPZ2JNAC2W2U/graph.json","fetch_events":"https://pith.science/api/pith-number/AWHYVVJC4SBMYRDPZ2JNAC2W2U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AWHYVVJC4SBMYRDPZ2JNAC2W2U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AWHYVVJC4SBMYRDPZ2JNAC2W2U/action/storage_attestation","attest_author":"https://pith.science/pith/AWHYVVJC4SBMYRDPZ2JNAC2W2U/action/author_attestation","sign_citation":"https://pith.science/pith/AWHYVVJC4SBMYRDPZ2JNAC2W2U/action/citation_signature","submit_replication":"https://pith.science/pith/AWHYVVJC4SBMYRDPZ2JNAC2W2U/action/replication_record"}},"created_at":"2026-07-09T00:19:21.149077+00:00","updated_at":"2026-07-09T00:19:21.149077+00:00"}