{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:M57FNZA3XKTF7DSQ3ZBFSIJAJC","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":"412d2a274449413fff107c1782a123d6cef70521289a3a80d1259c1741885a8d","cross_cats_sorted":["cs.IR","q-bio.QM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-03T07:58:17Z","title_canon_sha256":"3b0b5c702f0b148c78c0122eb5c2c4f35c65e3ef1a18bd29381faaf20d3484c0"},"schema_version":"1.0","source":{"id":"2206.01436","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.01436","created_at":"2026-07-05T04:28:47Z"},{"alias_kind":"arxiv_version","alias_value":"2206.01436v1","created_at":"2026-07-05T04:28:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.01436","created_at":"2026-07-05T04:28:47Z"},{"alias_kind":"pith_short_12","alias_value":"M57FNZA3XKTF","created_at":"2026-07-05T04:28:47Z"},{"alias_kind":"pith_short_16","alias_value":"M57FNZA3XKTF7DSQ","created_at":"2026-07-05T04:28:47Z"},{"alias_kind":"pith_short_8","alias_value":"M57FNZA3","created_at":"2026-07-05T04:28:47Z"}],"graph_snapshots":[{"event_id":"sha256:15d2e90fa55b16bc0e0151b5ecf6b3ad5e100d1c1d39d286a3e7ddb1b1cfbaf8","target":"graph","created_at":"2026-07-05T04:28:47Z","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/2206.01436/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid growth of electronic health record (EHR) datasets opens up promising opportunities to understand human diseases in a systematic way. However, effective extraction of clinical knowledge from the EHR data has been hindered by its sparsity and noisy information. We present KG-ETM, an end-to-end knowledge graph-based multimodal embedded topic model. KG-ETM distills latent disease topics from EHR data by learning the embedding from the medical knowledge graphs. We applied KG-ETM to a large-scale EHR dataset consisting of over 1 million patients. We evaluated its performance based on EHR r","authors_text":"Ahmad Pesaranghader, Aman Verma, David Buckeridge, Yue Li, Yuesong Zou","cross_cats":["cs.IR","q-bio.QM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-03T07:58:17Z","title":"Modeling electronic health record data using a knowledge-graph-embedded topic model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.01436","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":"sha256:701e1f2be077d87b611e2243da1ad6872cdbb70e7b7e07fa16de7b6989236717","target":"record","created_at":"2026-07-05T04:28:47Z","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":"412d2a274449413fff107c1782a123d6cef70521289a3a80d1259c1741885a8d","cross_cats_sorted":["cs.IR","q-bio.QM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-03T07:58:17Z","title_canon_sha256":"3b0b5c702f0b148c78c0122eb5c2c4f35c65e3ef1a18bd29381faaf20d3484c0"},"schema_version":"1.0","source":{"id":"2206.01436","kind":"arxiv","version":1}},"canonical_sha256":"677e56e41bbaa65f8e50de425921204887d456c27650544188713c38f6d43cf9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"677e56e41bbaa65f8e50de425921204887d456c27650544188713c38f6d43cf9","first_computed_at":"2026-07-05T04:28:47.610613Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:28:47.610613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/vfaA2xmILZt1PLs1fyPwISey+5ToBV/Thg7W+yKUujXh0OTmHULaeOvsEtxOmsQ8EmkpQUuJ2qRZkGWooIHDw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:28:47.611115Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.01436","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:701e1f2be077d87b611e2243da1ad6872cdbb70e7b7e07fa16de7b6989236717","sha256:15d2e90fa55b16bc0e0151b5ecf6b3ad5e100d1c1d39d286a3e7ddb1b1cfbaf8"],"state_sha256":"f6be853c57107527fd6c88ac69cabadbe46becf71c8c1cfbe04a89a32463438e"}