{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:WAEE6QVR6WM3MZEVPEXBHJVKY4","short_pith_number":"pith:WAEE6QVR","canonical_record":{"source":{"id":"2203.09994","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-18T14:45:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"98ce2d403d85095ff8a3a8bde17d4864f2ec092394dc27510d0798b594cd4663","abstract_canon_sha256":"4e135cbdaa626d32d8dfa768b9d5b359773cbdc829efd2027b5a256d89062093"},"schema_version":"1.0"},"canonical_sha256":"b0084f42b1f599b66495792e13a6aac70cfd5e8952fbb8a6cadfd318e875d757","source":{"kind":"arxiv","id":"2203.09994","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.09994","created_at":"2026-07-05T04:06:26Z"},{"alias_kind":"arxiv_version","alias_value":"2203.09994v1","created_at":"2026-07-05T04:06:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.09994","created_at":"2026-07-05T04:06:26Z"},{"alias_kind":"pith_short_12","alias_value":"WAEE6QVR6WM3","created_at":"2026-07-05T04:06:26Z"},{"alias_kind":"pith_short_16","alias_value":"WAEE6QVR6WM3MZEV","created_at":"2026-07-05T04:06:26Z"},{"alias_kind":"pith_short_8","alias_value":"WAEE6QVR","created_at":"2026-07-05T04:06:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:WAEE6QVR6WM3MZEVPEXBHJVKY4","target":"record","payload":{"canonical_record":{"source":{"id":"2203.09994","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-18T14:45:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"98ce2d403d85095ff8a3a8bde17d4864f2ec092394dc27510d0798b594cd4663","abstract_canon_sha256":"4e135cbdaa626d32d8dfa768b9d5b359773cbdc829efd2027b5a256d89062093"},"schema_version":"1.0"},"canonical_sha256":"b0084f42b1f599b66495792e13a6aac70cfd5e8952fbb8a6cadfd318e875d757","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:26.528151Z","signature_b64":"8vz6seixZsDs5U2Uu44He/F6HE/ogR+0eldKg6leLdInWApFpV1NVrKyFDlKu1hF2mVAjVGByuKMKNuwxPwkBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0084f42b1f599b66495792e13a6aac70cfd5e8952fbb8a6cadfd318e875d757","last_reissued_at":"2026-07-05T04:06:26.527632Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:26.527632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.09994","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:06:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qI4CAEnyTJLeq/8xnSsk/kmxCWHRFtam/58HAUmIiXiFxfI/VgmQikFzt3fbYlVSkSGkzgec73F/caMxdozeBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T16:11:14.921666Z"},"content_sha256":"669aa3723d7df333a8a1bcbf8d1aecb9fcf3fe4af7b54a44c87f9b3b842ab852","schema_version":"1.0","event_id":"sha256:669aa3723d7df333a8a1bcbf8d1aecb9fcf3fe4af7b54a44c87f9b3b842ab852"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:WAEE6QVR6WM3MZEVPEXBHJVKY4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Graph-Text Multi-Modal Pre-training for Medical Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Edward Choi, Jiho Kim, Seongsu Bae, Sungjin Park, Tackeun Kim","submitted_at":"2022-03-18T14:45:42Z","abstract_excerpt":"As the volume of Electronic Health Records (EHR) sharply grows, there has been emerging interest in learning the representation of EHR for healthcare applications. Representation learning of EHR requires appropriate modeling of the two dominant modalities in EHR: structured data and unstructured text. In this paper, we present MedGTX, a pre-trained model for multi-modal representation learning of the structured and textual EHR data. MedGTX uses a novel graph encoder to exploit the graphical nature of structured EHR data, and a text encoder to handle unstructured text, and a cross-modal encoder"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.09994","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/2203.09994/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:06:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9lHr1g07mmPHbGDNjTH3ckszdMwYkbNPa7aLyVpVwpeVcGtQ2zRbj3cPEBrVrHl0VP8Ei5hTzayP3Dz8C8WcAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T16:11:14.922070Z"},"content_sha256":"83f4072831349651d0b791c2a43cb3ab9d53c5f4f8b0290a6aefb8de5b105a68","schema_version":"1.0","event_id":"sha256:83f4072831349651d0b791c2a43cb3ab9d53c5f4f8b0290a6aefb8de5b105a68"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WAEE6QVR6WM3MZEVPEXBHJVKY4/bundle.json","state_url":"https://pith.science/pith/WAEE6QVR6WM3MZEVPEXBHJVKY4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WAEE6QVR6WM3MZEVPEXBHJVKY4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-13T16:11:14Z","links":{"resolver":"https://pith.science/pith/WAEE6QVR6WM3MZEVPEXBHJVKY4","bundle":"https://pith.science/pith/WAEE6QVR6WM3MZEVPEXBHJVKY4/bundle.json","state":"https://pith.science/pith/WAEE6QVR6WM3MZEVPEXBHJVKY4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WAEE6QVR6WM3MZEVPEXBHJVKY4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:WAEE6QVR6WM3MZEVPEXBHJVKY4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4e135cbdaa626d32d8dfa768b9d5b359773cbdc829efd2027b5a256d89062093","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-18T14:45:42Z","title_canon_sha256":"98ce2d403d85095ff8a3a8bde17d4864f2ec092394dc27510d0798b594cd4663"},"schema_version":"1.0","source":{"id":"2203.09994","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.09994","created_at":"2026-07-05T04:06:26Z"},{"alias_kind":"arxiv_version","alias_value":"2203.09994v1","created_at":"2026-07-05T04:06:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.09994","created_at":"2026-07-05T04:06:26Z"},{"alias_kind":"pith_short_12","alias_value":"WAEE6QVR6WM3","created_at":"2026-07-05T04:06:26Z"},{"alias_kind":"pith_short_16","alias_value":"WAEE6QVR6WM3MZEV","created_at":"2026-07-05T04:06:26Z"},{"alias_kind":"pith_short_8","alias_value":"WAEE6QVR","created_at":"2026-07-05T04:06:26Z"}],"graph_snapshots":[{"event_id":"sha256:83f4072831349651d0b791c2a43cb3ab9d53c5f4f8b0290a6aefb8de5b105a68","target":"graph","created_at":"2026-07-05T04:06:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2203.09994/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As the volume of Electronic Health Records (EHR) sharply grows, there has been emerging interest in learning the representation of EHR for healthcare applications. Representation learning of EHR requires appropriate modeling of the two dominant modalities in EHR: structured data and unstructured text. In this paper, we present MedGTX, a pre-trained model for multi-modal representation learning of the structured and textual EHR data. MedGTX uses a novel graph encoder to exploit the graphical nature of structured EHR data, and a text encoder to handle unstructured text, and a cross-modal encoder","authors_text":"Edward Choi, Jiho Kim, Seongsu Bae, Sungjin Park, Tackeun Kim","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-18T14:45:42Z","title":"Graph-Text Multi-Modal Pre-training for Medical Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.09994","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:669aa3723d7df333a8a1bcbf8d1aecb9fcf3fe4af7b54a44c87f9b3b842ab852","target":"record","created_at":"2026-07-05T04:06:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4e135cbdaa626d32d8dfa768b9d5b359773cbdc829efd2027b5a256d89062093","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-18T14:45:42Z","title_canon_sha256":"98ce2d403d85095ff8a3a8bde17d4864f2ec092394dc27510d0798b594cd4663"},"schema_version":"1.0","source":{"id":"2203.09994","kind":"arxiv","version":1}},"canonical_sha256":"b0084f42b1f599b66495792e13a6aac70cfd5e8952fbb8a6cadfd318e875d757","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0084f42b1f599b66495792e13a6aac70cfd5e8952fbb8a6cadfd318e875d757","first_computed_at":"2026-07-05T04:06:26.527632Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:06:26.527632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8vz6seixZsDs5U2Uu44He/F6HE/ogR+0eldKg6leLdInWApFpV1NVrKyFDlKu1hF2mVAjVGByuKMKNuwxPwkBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:06:26.528151Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.09994","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:669aa3723d7df333a8a1bcbf8d1aecb9fcf3fe4af7b54a44c87f9b3b842ab852","sha256:83f4072831349651d0b791c2a43cb3ab9d53c5f4f8b0290a6aefb8de5b105a68"],"state_sha256":"793861b2473b8478542de5e85852a04e471190ec3cdaaacb0220ae5d19a06b6b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ESwXujcJs2tp7p2n7P91x7zTHyqN+jEXJQ2SgAzgTqwSe+CUuwud8FX5HNdYRFYoclSjburKWSAXVspcN07FCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T16:11:14.924114Z","bundle_sha256":"f246a396fc5990f3d90216b368d26a929dbfeb765ca3c93418a9ac67fd5c4d57"}}