{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5HMDIHUZSWHXSBJ6B5UF53ZUT2","short_pith_number":"pith:5HMDIHUZ","schema_version":"1.0","canonical_sha256":"e9d8341e99958f79053e0f685eef349eb8c1b86b12adc0698cda71e277c7b09c","source":{"kind":"arxiv","id":"2310.18652","version":2},"attestation_state":"computed","paper":{"title":"EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Daeun Kyung, Edward Choi, Eric I-Chao Chang, Eunbyeol Cho, Gyubok Lee, Jaehee Ryu, JungWoo Oh, Lei Ji, Seongsu Bae, Sunjun Kweon, Tackeun Kim","submitted_at":"2023-10-28T09:42:04Z","abstract_excerpt":"Electronic Health Records (EHRs), which contain patients' medical histories in various multi-modal formats, often overlook the potential for joint reasoning across imaging and table modalities underexplored in current EHR Question Answering (QA) systems. In this paper, we introduce EHRXQA, a novel multi-modal question answering dataset combining structured EHRs and chest X-ray images. To develop our dataset, we first construct two uni-modal resources: 1) The MIMIC-CXR-VQA dataset, our newly created medical visual question answering (VQA) benchmark, specifically designed to augment the imaging "},"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":"2310.18652","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-28T09:42:04Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"7721d97575b5bd6b9c547b0d9680d04e793321265e8054209d47fad00f29910a","abstract_canon_sha256":"28525af40565579f805f565f76d879a0f34cf0e09d283cfcbf0088999a3cbbad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:52.097747Z","signature_b64":"ouP3ILOmlt69CuGHWRXIrsq1gDiiUnB0JclSFcbg2GhZ48AkTjrB29qRkvOL15h7P1GHw8bopAki0V9nxT6GAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9d8341e99958f79053e0f685eef349eb8c1b86b12adc0698cda71e277c7b09c","last_reissued_at":"2026-07-05T07:27:52.097252Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:52.097252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Daeun Kyung, Edward Choi, Eric I-Chao Chang, Eunbyeol Cho, Gyubok Lee, Jaehee Ryu, JungWoo Oh, Lei Ji, Seongsu Bae, Sunjun Kweon, Tackeun Kim","submitted_at":"2023-10-28T09:42:04Z","abstract_excerpt":"Electronic Health Records (EHRs), which contain patients' medical histories in various multi-modal formats, often overlook the potential for joint reasoning across imaging and table modalities underexplored in current EHR Question Answering (QA) systems. In this paper, we introduce EHRXQA, a novel multi-modal question answering dataset combining structured EHRs and chest X-ray images. To develop our dataset, we first construct two uni-modal resources: 1) The MIMIC-CXR-VQA dataset, our newly created medical visual question answering (VQA) benchmark, specifically designed to augment the imaging "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18652","kind":"arxiv","version":2},"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/2310.18652/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":"2310.18652","created_at":"2026-07-05T07:27:52.097324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.18652v2","created_at":"2026-07-05T07:27:52.097324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18652","created_at":"2026-07-05T07:27:52.097324+00:00"},{"alias_kind":"pith_short_12","alias_value":"5HMDIHUZSWHX","created_at":"2026-07-05T07:27:52.097324+00:00"},{"alias_kind":"pith_short_16","alias_value":"5HMDIHUZSWHXSBJ6","created_at":"2026-07-05T07:27:52.097324+00:00"},{"alias_kind":"pith_short_8","alias_value":"5HMDIHUZ","created_at":"2026-07-05T07:27:52.097324+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.21027","citing_title":"HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering","ref_index":176,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5HMDIHUZSWHXSBJ6B5UF53ZUT2","json":"https://pith.science/pith/5HMDIHUZSWHXSBJ6B5UF53ZUT2.json","graph_json":"https://pith.science/api/pith-number/5HMDIHUZSWHXSBJ6B5UF53ZUT2/graph.json","events_json":"https://pith.science/api/pith-number/5HMDIHUZSWHXSBJ6B5UF53ZUT2/events.json","paper":"https://pith.science/paper/5HMDIHUZ"},"agent_actions":{"view_html":"https://pith.science/pith/5HMDIHUZSWHXSBJ6B5UF53ZUT2","download_json":"https://pith.science/pith/5HMDIHUZSWHXSBJ6B5UF53ZUT2.json","view_paper":"https://pith.science/paper/5HMDIHUZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.18652&json=true","fetch_graph":"https://pith.science/api/pith-number/5HMDIHUZSWHXSBJ6B5UF53ZUT2/graph.json","fetch_events":"https://pith.science/api/pith-number/5HMDIHUZSWHXSBJ6B5UF53ZUT2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5HMDIHUZSWHXSBJ6B5UF53ZUT2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5HMDIHUZSWHXSBJ6B5UF53ZUT2/action/storage_attestation","attest_author":"https://pith.science/pith/5HMDIHUZSWHXSBJ6B5UF53ZUT2/action/author_attestation","sign_citation":"https://pith.science/pith/5HMDIHUZSWHXSBJ6B5UF53ZUT2/action/citation_signature","submit_replication":"https://pith.science/pith/5HMDIHUZSWHXSBJ6B5UF53ZUT2/action/replication_record"}},"created_at":"2026-07-05T07:27:52.097324+00:00","updated_at":"2026-07-05T07:27:52.097324+00:00"}