{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:U6KS52DDTZAXLN7VDD6WJOHFSZ","short_pith_number":"pith:U6KS52DD","schema_version":"1.0","canonical_sha256":"a7952ee8639e4175b7f518fd64b8e5967ba06a8a1b2d393f2eed97009eb94f56","source":{"kind":"arxiv","id":"2108.03625","version":3},"attestation_state":"computed","paper":{"title":"Unifying Heterogeneous Electronic Health Records Systems via Text-Based Code Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Edward Choi, Jiyoung Lee, JungWoo Oh, Kyunghoon Hur, Wesley Price, Young-Hak Kim","submitted_at":"2021-08-08T12:47:42Z","abstract_excerpt":"Substantial increase in the use of Electronic Health Records (EHRs) has opened new frontiers for predictive healthcare. However, while EHR systems are nearly ubiquitous, they lack a unified code system for representing medical concepts. Heterogeneous formats of EHR present a substantial barrier for the training and deployment of state-of-the-art deep learning models at scale. To overcome this problem, we introduce Description-based Embedding, DescEmb, a code-agnostic description-based representation learning framework for predictive modeling on EHR. DescEmb takes advantage of the flexibility o"},"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":"2108.03625","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-08T12:47:42Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"acd01542e30fc96142324e5188f9ef613cd1b23d745bae90f5769262fdd6f880","abstract_canon_sha256":"165f862c029dfaaba2b37250372e740445ce1002cabc275367799b10fe21d2b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:16.253288Z","signature_b64":"VOMmZZahZWOPdRxlYwnei2kWpKy8FGmxT+/maWgEDilJAL4HtD+LqEb743jzEPP047YBWjtlYvK7xMlyu6TXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7952ee8639e4175b7f518fd64b8e5967ba06a8a1b2d393f2eed97009eb94f56","last_reissued_at":"2026-07-05T04:06:16.252745Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:16.252745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unifying Heterogeneous Electronic Health Records Systems via Text-Based Code Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Edward Choi, Jiyoung Lee, JungWoo Oh, Kyunghoon Hur, Wesley Price, Young-Hak Kim","submitted_at":"2021-08-08T12:47:42Z","abstract_excerpt":"Substantial increase in the use of Electronic Health Records (EHRs) has opened new frontiers for predictive healthcare. However, while EHR systems are nearly ubiquitous, they lack a unified code system for representing medical concepts. Heterogeneous formats of EHR present a substantial barrier for the training and deployment of state-of-the-art deep learning models at scale. To overcome this problem, we introduce Description-based Embedding, DescEmb, a code-agnostic description-based representation learning framework for predictive modeling on EHR. DescEmb takes advantage of the flexibility o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.03625","kind":"arxiv","version":3},"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/2108.03625/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":"2108.03625","created_at":"2026-07-05T04:06:16.252806+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.03625v3","created_at":"2026-07-05T04:06:16.252806+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.03625","created_at":"2026-07-05T04:06:16.252806+00:00"},{"alias_kind":"pith_short_12","alias_value":"U6KS52DDTZAX","created_at":"2026-07-05T04:06:16.252806+00:00"},{"alias_kind":"pith_short_16","alias_value":"U6KS52DDTZAXLN7V","created_at":"2026-07-05T04:06:16.252806+00:00"},{"alias_kind":"pith_short_8","alias_value":"U6KS52DD","created_at":"2026-07-05T04:06:16.252806+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.16775","citing_title":"Representation Before Training: A Fixed-Budget Benchmark for Generative Medical Event Models","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U6KS52DDTZAXLN7VDD6WJOHFSZ","json":"https://pith.science/pith/U6KS52DDTZAXLN7VDD6WJOHFSZ.json","graph_json":"https://pith.science/api/pith-number/U6KS52DDTZAXLN7VDD6WJOHFSZ/graph.json","events_json":"https://pith.science/api/pith-number/U6KS52DDTZAXLN7VDD6WJOHFSZ/events.json","paper":"https://pith.science/paper/U6KS52DD"},"agent_actions":{"view_html":"https://pith.science/pith/U6KS52DDTZAXLN7VDD6WJOHFSZ","download_json":"https://pith.science/pith/U6KS52DDTZAXLN7VDD6WJOHFSZ.json","view_paper":"https://pith.science/paper/U6KS52DD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.03625&json=true","fetch_graph":"https://pith.science/api/pith-number/U6KS52DDTZAXLN7VDD6WJOHFSZ/graph.json","fetch_events":"https://pith.science/api/pith-number/U6KS52DDTZAXLN7VDD6WJOHFSZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U6KS52DDTZAXLN7VDD6WJOHFSZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U6KS52DDTZAXLN7VDD6WJOHFSZ/action/storage_attestation","attest_author":"https://pith.science/pith/U6KS52DDTZAXLN7VDD6WJOHFSZ/action/author_attestation","sign_citation":"https://pith.science/pith/U6KS52DDTZAXLN7VDD6WJOHFSZ/action/citation_signature","submit_replication":"https://pith.science/pith/U6KS52DDTZAXLN7VDD6WJOHFSZ/action/replication_record"}},"created_at":"2026-07-05T04:06:16.252806+00:00","updated_at":"2026-07-05T04:06:16.252806+00:00"}