{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NMYKPDDKOAAFNCK5N6GAMMRQM5","short_pith_number":"pith:NMYKPDDK","schema_version":"1.0","canonical_sha256":"6b30a78c6a700056895d6f8c063230677351adf02406f6dfe81df1fa838c8b61","source":{"kind":"arxiv","id":"2508.09182","version":1},"attestation_state":"computed","paper":{"title":"MedPatch: Confidence-Guided Multi-Stage Fusion for Multimodal Clinical Data","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Baraa Al Jorf, Farah Shamout","submitted_at":"2025-08-07T12:46:26Z","abstract_excerpt":"Clinical decision-making relies on the integration of information across various data modalities, such as clinical time-series, medical images and textual reports. Compared to other domains, real-world medical data is heterogeneous in nature, limited in size, and sparse due to missing modalities. This significantly limits model performance in clinical prediction tasks. Inspired by clinical workflows, we introduce MedPatch, a multi-stage multimodal fusion architecture, which seamlessly integrates multiple modalities via confidence-guided patching. MedPatch comprises three main components: (i) a"},"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":"2508.09182","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.IV","submitted_at":"2025-08-07T12:46:26Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"4b4bf510b55c11a449d29c54042039489c47ed3b2f9cfc55f22c3f4cdd851cb2","abstract_canon_sha256":"4eb69d90257d756831fdf42f1b680b31e2699b5f39c473cda87f0c6b63682025"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:09.552776Z","signature_b64":"Oa/WN6MBTZn++rGtEsXUzlvM2D8dRvO6R1OIM/chFMUkiRLGnAHR9WelCsp7uA5pQfXn5nDtwkw6PEJo39fpDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b30a78c6a700056895d6f8c063230677351adf02406f6dfe81df1fa838c8b61","last_reissued_at":"2026-07-05T11:53:09.552279Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:09.552279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedPatch: Confidence-Guided Multi-Stage Fusion for Multimodal Clinical Data","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Baraa Al Jorf, Farah Shamout","submitted_at":"2025-08-07T12:46:26Z","abstract_excerpt":"Clinical decision-making relies on the integration of information across various data modalities, such as clinical time-series, medical images and textual reports. Compared to other domains, real-world medical data is heterogeneous in nature, limited in size, and sparse due to missing modalities. This significantly limits model performance in clinical prediction tasks. Inspired by clinical workflows, we introduce MedPatch, a multi-stage multimodal fusion architecture, which seamlessly integrates multiple modalities via confidence-guided patching. MedPatch comprises three main components: (i) a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09182","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/2508.09182/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":"2508.09182","created_at":"2026-07-05T11:53:09.552339+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.09182v1","created_at":"2026-07-05T11:53:09.552339+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09182","created_at":"2026-07-05T11:53:09.552339+00:00"},{"alias_kind":"pith_short_12","alias_value":"NMYKPDDKOAAF","created_at":"2026-07-05T11:53:09.552339+00:00"},{"alias_kind":"pith_short_16","alias_value":"NMYKPDDKOAAFNCK5","created_at":"2026-07-05T11:53:09.552339+00:00"},{"alias_kind":"pith_short_8","alias_value":"NMYKPDDK","created_at":"2026-07-05T11:53:09.552339+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.16878","citing_title":"OC-Distill: Ontology-aware Contrastive Learning with Cross-Modal Distillation for ICU Risk Prediction","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NMYKPDDKOAAFNCK5N6GAMMRQM5","json":"https://pith.science/pith/NMYKPDDKOAAFNCK5N6GAMMRQM5.json","graph_json":"https://pith.science/api/pith-number/NMYKPDDKOAAFNCK5N6GAMMRQM5/graph.json","events_json":"https://pith.science/api/pith-number/NMYKPDDKOAAFNCK5N6GAMMRQM5/events.json","paper":"https://pith.science/paper/NMYKPDDK"},"agent_actions":{"view_html":"https://pith.science/pith/NMYKPDDKOAAFNCK5N6GAMMRQM5","download_json":"https://pith.science/pith/NMYKPDDKOAAFNCK5N6GAMMRQM5.json","view_paper":"https://pith.science/paper/NMYKPDDK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.09182&json=true","fetch_graph":"https://pith.science/api/pith-number/NMYKPDDKOAAFNCK5N6GAMMRQM5/graph.json","fetch_events":"https://pith.science/api/pith-number/NMYKPDDKOAAFNCK5N6GAMMRQM5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NMYKPDDKOAAFNCK5N6GAMMRQM5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NMYKPDDKOAAFNCK5N6GAMMRQM5/action/storage_attestation","attest_author":"https://pith.science/pith/NMYKPDDKOAAFNCK5N6GAMMRQM5/action/author_attestation","sign_citation":"https://pith.science/pith/NMYKPDDKOAAFNCK5N6GAMMRQM5/action/citation_signature","submit_replication":"https://pith.science/pith/NMYKPDDKOAAFNCK5N6GAMMRQM5/action/replication_record"}},"created_at":"2026-07-05T11:53:09.552339+00:00","updated_at":"2026-07-05T11:53:09.552339+00:00"}