{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JDEWRNQMEBEAJBAHWOZWFI52NA","short_pith_number":"pith:JDEWRNQM","schema_version":"1.0","canonical_sha256":"48c968b60c2048048407b3b362a3ba68104b24a1322e9927e07951e9e4bbabd1","source":{"kind":"arxiv","id":"2607.15380","version":1},"attestation_state":"computed","paper":{"title":"Large Language Models as Unified Multimodal Learners for Clinical Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ajay Madhavan Ravichandran, Aljoscha Burchardt, Bilgin Osmandoja, Klaus Netter, Klemens Budde, Roland Roller, Sebastian M\\\"oller, Tobias Strapatsas","submitted_at":"2026-07-16T18:28:23Z","abstract_excerpt":"Electronic health records combine free-text clinical narratives with structured measurements such as vital signs, laboratory values, and comorbidities. Yet most clinical prediction systems still rely on task-specific fusion architectures, pairing dedicated encoders for each modality with learned combination mechanisms that must be re-engineered for every new task and clinical setting. We propose a simpler alternative: convert all patient data, regardless of modality, into a single natural language sequence and fine-tune a pretrained language model end-to-end, with no architectural modification"},"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":"2607.15380","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T18:28:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"86402435fec2d20fa929a470042c9f85d3c16a8331102577c190285e21936d66","abstract_canon_sha256":"568ddce96442cec4f44d1de470a0b196e5963a6746f40ea3ef3e2e95e0679e65"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-20T00:18:30.413520Z","signature_b64":"O6j/JvCEZRp24DI9bhhWK+PFkKI7Y0BlOlSwX3mwVHZ4DFnF/rrF7bZr9Kjr2jnxq8bDLnEQsv8Y/kZocuF2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48c968b60c2048048407b3b362a3ba68104b24a1322e9927e07951e9e4bbabd1","last_reissued_at":"2026-07-20T00:18:30.412710Z","signature_status":"signed_v1","first_computed_at":"2026-07-20T00:18:30.412710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models as Unified Multimodal Learners for Clinical Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ajay Madhavan Ravichandran, Aljoscha Burchardt, Bilgin Osmandoja, Klaus Netter, Klemens Budde, Roland Roller, Sebastian M\\\"oller, Tobias Strapatsas","submitted_at":"2026-07-16T18:28:23Z","abstract_excerpt":"Electronic health records combine free-text clinical narratives with structured measurements such as vital signs, laboratory values, and comorbidities. Yet most clinical prediction systems still rely on task-specific fusion architectures, pairing dedicated encoders for each modality with learned combination mechanisms that must be re-engineered for every new task and clinical setting. We propose a simpler alternative: convert all patient data, regardless of modality, into a single natural language sequence and fine-tune a pretrained language model end-to-end, with no architectural modification"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15380","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/2607.15380/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":"2607.15380","created_at":"2026-07-20T00:18:30.413114+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.15380v1","created_at":"2026-07-20T00:18:30.413114+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15380","created_at":"2026-07-20T00:18:30.413114+00:00"},{"alias_kind":"pith_short_12","alias_value":"JDEWRNQMEBEA","created_at":"2026-07-20T00:18:30.413114+00:00"},{"alias_kind":"pith_short_16","alias_value":"JDEWRNQMEBEAJBAH","created_at":"2026-07-20T00:18:30.413114+00:00"},{"alias_kind":"pith_short_8","alias_value":"JDEWRNQM","created_at":"2026-07-20T00:18:30.413114+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/JDEWRNQMEBEAJBAHWOZWFI52NA","json":"https://pith.science/pith/JDEWRNQMEBEAJBAHWOZWFI52NA.json","graph_json":"https://pith.science/api/pith-number/JDEWRNQMEBEAJBAHWOZWFI52NA/graph.json","events_json":"https://pith.science/api/pith-number/JDEWRNQMEBEAJBAHWOZWFI52NA/events.json","paper":"https://pith.science/paper/JDEWRNQM"},"agent_actions":{"view_html":"https://pith.science/pith/JDEWRNQMEBEAJBAHWOZWFI52NA","download_json":"https://pith.science/pith/JDEWRNQMEBEAJBAHWOZWFI52NA.json","view_paper":"https://pith.science/paper/JDEWRNQM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.15380&json=true","fetch_graph":"https://pith.science/api/pith-number/JDEWRNQMEBEAJBAHWOZWFI52NA/graph.json","fetch_events":"https://pith.science/api/pith-number/JDEWRNQMEBEAJBAHWOZWFI52NA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JDEWRNQMEBEAJBAHWOZWFI52NA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JDEWRNQMEBEAJBAHWOZWFI52NA/action/storage_attestation","attest_author":"https://pith.science/pith/JDEWRNQMEBEAJBAHWOZWFI52NA/action/author_attestation","sign_citation":"https://pith.science/pith/JDEWRNQMEBEAJBAHWOZWFI52NA/action/citation_signature","submit_replication":"https://pith.science/pith/JDEWRNQMEBEAJBAHWOZWFI52NA/action/replication_record"}},"created_at":"2026-07-20T00:18:30.413114+00:00","updated_at":"2026-07-20T00:18:30.413114+00:00"}