{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7DR2XATGUB3OG235X45TYT5I3M","short_pith_number":"pith:7DR2XATG","schema_version":"1.0","canonical_sha256":"f8e3ab8266a076e36b7dbf3b3c4fa8db00757adf653a4f54e90d7226a68c847d","source":{"kind":"arxiv","id":"2503.09498","version":1},"attestation_state":"computed","paper":{"title":"Towards Robust Multimodal Representation: A Unified Approach with Adaptive Experts and Alignment","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Donald E. Brown, Jiebei Liu, Nazanin Moradinasab, Sana Syed, Saurav Sengupta","submitted_at":"2025-03-12T16:03:00Z","abstract_excerpt":"Healthcare relies on multiple types of data, such as medical images, genetic information, and clinical records, to improve diagnosis and treatment. However, missing data is a common challenge due to privacy restrictions, cost, and technical issues, making many existing multi-modal models unreliable. To address this, we propose a new multi-model model called Mixture of Experts, Symmetric Aligning, and Reconstruction (MoSARe), a deep learning framework that handles incomplete multimodal data while maintaining high accuracy. MoSARe integrates expert selection, cross-modal attention, and contrasti"},"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":"2503.09498","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-12T16:03:00Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"be27f376875301168879d0e4866176b03474752ae867ef04edc5d10631f49185","abstract_canon_sha256":"d81178ae5280722155ec6441fc690611d66689b1e7452567da24b2d7df5e72a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:57.193084Z","signature_b64":"r4Z6C4PGI1cgNPPjpYZ3z5yfOkQ7dAfWlf5+9u60Vkhdl1pDS89Y7Ye1u6u0k/Crd6bXXYwMm8y1lqcAknBzBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8e3ab8266a076e36b7dbf3b3c4fa8db00757adf653a4f54e90d7226a68c847d","last_reissued_at":"2026-07-05T10:29:57.192479Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:57.192479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Robust Multimodal Representation: A Unified Approach with Adaptive Experts and Alignment","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Donald E. Brown, Jiebei Liu, Nazanin Moradinasab, Sana Syed, Saurav Sengupta","submitted_at":"2025-03-12T16:03:00Z","abstract_excerpt":"Healthcare relies on multiple types of data, such as medical images, genetic information, and clinical records, to improve diagnosis and treatment. However, missing data is a common challenge due to privacy restrictions, cost, and technical issues, making many existing multi-modal models unreliable. To address this, we propose a new multi-model model called Mixture of Experts, Symmetric Aligning, and Reconstruction (MoSARe), a deep learning framework that handles incomplete multimodal data while maintaining high accuracy. MoSARe integrates expert selection, cross-modal attention, and contrasti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.09498","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/2503.09498/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":"2503.09498","created_at":"2026-07-05T10:29:57.192553+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.09498v1","created_at":"2026-07-05T10:29:57.192553+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.09498","created_at":"2026-07-05T10:29:57.192553+00:00"},{"alias_kind":"pith_short_12","alias_value":"7DR2XATGUB3O","created_at":"2026-07-05T10:29:57.192553+00:00"},{"alias_kind":"pith_short_16","alias_value":"7DR2XATGUB3OG235","created_at":"2026-07-05T10:29:57.192553+00:00"},{"alias_kind":"pith_short_8","alias_value":"7DR2XATG","created_at":"2026-07-05T10:29:57.192553+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.04614","citing_title":"A Clinical Point Cloud Paradigm for In-Hospital Mortality Prediction from Multi-Level Incomplete Multimodal EHRs","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7DR2XATGUB3OG235X45TYT5I3M","json":"https://pith.science/pith/7DR2XATGUB3OG235X45TYT5I3M.json","graph_json":"https://pith.science/api/pith-number/7DR2XATGUB3OG235X45TYT5I3M/graph.json","events_json":"https://pith.science/api/pith-number/7DR2XATGUB3OG235X45TYT5I3M/events.json","paper":"https://pith.science/paper/7DR2XATG"},"agent_actions":{"view_html":"https://pith.science/pith/7DR2XATGUB3OG235X45TYT5I3M","download_json":"https://pith.science/pith/7DR2XATGUB3OG235X45TYT5I3M.json","view_paper":"https://pith.science/paper/7DR2XATG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.09498&json=true","fetch_graph":"https://pith.science/api/pith-number/7DR2XATGUB3OG235X45TYT5I3M/graph.json","fetch_events":"https://pith.science/api/pith-number/7DR2XATGUB3OG235X45TYT5I3M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7DR2XATGUB3OG235X45TYT5I3M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7DR2XATGUB3OG235X45TYT5I3M/action/storage_attestation","attest_author":"https://pith.science/pith/7DR2XATGUB3OG235X45TYT5I3M/action/author_attestation","sign_citation":"https://pith.science/pith/7DR2XATGUB3OG235X45TYT5I3M/action/citation_signature","submit_replication":"https://pith.science/pith/7DR2XATGUB3OG235X45TYT5I3M/action/replication_record"}},"created_at":"2026-07-05T10:29:57.192553+00:00","updated_at":"2026-07-05T10:29:57.192553+00:00"}