{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:OWGSGDIOJHHOOJSMWSVVUJIIOQ","short_pith_number":"pith:OWGSGDIO","canonical_record":{"source":{"id":"2212.06040","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-14T14:59:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"94863def68de53145cc3191eae18f2171490f23633db9c2e93436b30ddbe69a1","abstract_canon_sha256":"4de488cc3e18cb4032707d82208f6a30a22d5ed8d0178fdcd24e3961255377d8"},"schema_version":"1.0"},"canonical_sha256":"758d230d0e49cee7264cb4ab5a25087439db944fb1996a16533711ff36040fbe","source":{"kind":"arxiv","id":"2212.06040","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.06040","created_at":"2026-07-05T05:24:22Z"},{"alias_kind":"arxiv_version","alias_value":"2212.06040v1","created_at":"2026-07-05T05:24:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.06040","created_at":"2026-07-05T05:24:22Z"},{"alias_kind":"pith_short_12","alias_value":"OWGSGDIOJHHO","created_at":"2026-07-05T05:24:22Z"},{"alias_kind":"pith_short_16","alias_value":"OWGSGDIOJHHOOJSM","created_at":"2026-07-05T05:24:22Z"},{"alias_kind":"pith_short_8","alias_value":"OWGSGDIO","created_at":"2026-07-05T05:24:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:OWGSGDIOJHHOOJSMWSVVUJIIOQ","target":"record","payload":{"canonical_record":{"source":{"id":"2212.06040","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-14T14:59:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"94863def68de53145cc3191eae18f2171490f23633db9c2e93436b30ddbe69a1","abstract_canon_sha256":"4de488cc3e18cb4032707d82208f6a30a22d5ed8d0178fdcd24e3961255377d8"},"schema_version":"1.0"},"canonical_sha256":"758d230d0e49cee7264cb4ab5a25087439db944fb1996a16533711ff36040fbe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:24:22.008066Z","signature_b64":"JTA8WF/oBeryVkxKedIwSRihvHO6K4zZABNT2O76GJuDZstR7HXquCtDq+M20cyLoq0yEqx2awpS5pFGcYfNBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"758d230d0e49cee7264cb4ab5a25087439db944fb1996a16533711ff36040fbe","last_reissued_at":"2026-07-05T05:24:22.007666Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:24:22.007666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.06040","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":"2026-07-05T05:24:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j84/UkGrn8APHIloP4PQdy1XYsqwIVAa8fUczEMNvAaepnvh3CpQaEte4sqUd9Le5nCrVlIGAi3mkD75Y2ZvAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T01:07:37.362948Z"},"content_sha256":"3606431660c74e2a8c656528ea2570e292ea3f718a6790b50d6672958b9bbae5","schema_version":"1.0","event_id":"sha256:3606431660c74e2a8c656528ea2570e292ea3f718a6790b50d6672958b9bbae5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:OWGSGDIOJHHOOJSMWSVVUJIIOQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semantic Decomposition Improves Learning of Large Language Models on EHR Data","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anna L. Decker, David A. Bloore, Jacob Oppenheim, Romane Gauriau","submitted_at":"2022-11-14T14:59:16Z","abstract_excerpt":"Electronic health records (EHR) are widely believed to hold a profusion of actionable insights, encrypted in an irregular, semi-structured format, amidst a loud noise background. To simplify learning patterns of health and disease, medical codes in EHR can be decomposed into semantic units connected by hierarchical graphs. Building on earlier synergy between Bidirectional Encoder Representations from Transformers (BERT) and Graph Attention Networks (GAT), we present H-BERT, which ingests complete graph tree expansions of hierarchical medical codes as opposed to only ingesting the leaves and pu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.06040","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/2212.06040/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":"2026-07-05T05:24:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3sqkzomMsexfTT6AeM+KRO3yIW46JXsRKspWmWgE443JVDd/A3xSazEEaIBtrOoywbyiF9BDph9Y4rPa2b8zBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T01:07:37.363380Z"},"content_sha256":"7b2728bf84d48c7c6f9cba3ad11cd3c3092c51744404e1ee77239bae1cfbd72b","schema_version":"1.0","event_id":"sha256:7b2728bf84d48c7c6f9cba3ad11cd3c3092c51744404e1ee77239bae1cfbd72b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OWGSGDIOJHHOOJSMWSVVUJIIOQ/bundle.json","state_url":"https://pith.science/pith/OWGSGDIOJHHOOJSMWSVVUJIIOQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OWGSGDIOJHHOOJSMWSVVUJIIOQ/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":"2026-07-11T01:07:37Z","links":{"resolver":"https://pith.science/pith/OWGSGDIOJHHOOJSMWSVVUJIIOQ","bundle":"https://pith.science/pith/OWGSGDIOJHHOOJSMWSVVUJIIOQ/bundle.json","state":"https://pith.science/pith/OWGSGDIOJHHOOJSMWSVVUJIIOQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OWGSGDIOJHHOOJSMWSVVUJIIOQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:OWGSGDIOJHHOOJSMWSVVUJIIOQ","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":"4de488cc3e18cb4032707d82208f6a30a22d5ed8d0178fdcd24e3961255377d8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-14T14:59:16Z","title_canon_sha256":"94863def68de53145cc3191eae18f2171490f23633db9c2e93436b30ddbe69a1"},"schema_version":"1.0","source":{"id":"2212.06040","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.06040","created_at":"2026-07-05T05:24:22Z"},{"alias_kind":"arxiv_version","alias_value":"2212.06040v1","created_at":"2026-07-05T05:24:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.06040","created_at":"2026-07-05T05:24:22Z"},{"alias_kind":"pith_short_12","alias_value":"OWGSGDIOJHHO","created_at":"2026-07-05T05:24:22Z"},{"alias_kind":"pith_short_16","alias_value":"OWGSGDIOJHHOOJSM","created_at":"2026-07-05T05:24:22Z"},{"alias_kind":"pith_short_8","alias_value":"OWGSGDIO","created_at":"2026-07-05T05:24:22Z"}],"graph_snapshots":[{"event_id":"sha256:7b2728bf84d48c7c6f9cba3ad11cd3c3092c51744404e1ee77239bae1cfbd72b","target":"graph","created_at":"2026-07-05T05:24:22Z","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/2212.06040/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Electronic health records (EHR) are widely believed to hold a profusion of actionable insights, encrypted in an irregular, semi-structured format, amidst a loud noise background. To simplify learning patterns of health and disease, medical codes in EHR can be decomposed into semantic units connected by hierarchical graphs. Building on earlier synergy between Bidirectional Encoder Representations from Transformers (BERT) and Graph Attention Networks (GAT), we present H-BERT, which ingests complete graph tree expansions of hierarchical medical codes as opposed to only ingesting the leaves and pu","authors_text":"Anna L. Decker, David A. Bloore, Jacob Oppenheim, Romane Gauriau","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-14T14:59:16Z","title":"Semantic Decomposition Improves Learning of Large Language Models on EHR Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.06040","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":"sha256:3606431660c74e2a8c656528ea2570e292ea3f718a6790b50d6672958b9bbae5","target":"record","created_at":"2026-07-05T05:24:22Z","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":"4de488cc3e18cb4032707d82208f6a30a22d5ed8d0178fdcd24e3961255377d8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-14T14:59:16Z","title_canon_sha256":"94863def68de53145cc3191eae18f2171490f23633db9c2e93436b30ddbe69a1"},"schema_version":"1.0","source":{"id":"2212.06040","kind":"arxiv","version":1}},"canonical_sha256":"758d230d0e49cee7264cb4ab5a25087439db944fb1996a16533711ff36040fbe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"758d230d0e49cee7264cb4ab5a25087439db944fb1996a16533711ff36040fbe","first_computed_at":"2026-07-05T05:24:22.007666Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:24:22.007666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JTA8WF/oBeryVkxKedIwSRihvHO6K4zZABNT2O76GJuDZstR7HXquCtDq+M20cyLoq0yEqx2awpS5pFGcYfNBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:24:22.008066Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.06040","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3606431660c74e2a8c656528ea2570e292ea3f718a6790b50d6672958b9bbae5","sha256:7b2728bf84d48c7c6f9cba3ad11cd3c3092c51744404e1ee77239bae1cfbd72b"],"state_sha256":"8fcc78f4dd22ce246aeb63b3d1ed88c36b19b97e8d9645f5e6fe41c30367dace"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qSCjSVh+oKeKzfw4CqD3ELLts0iSBrECzTcJRk3ousXJiRPmtP/ACoONAAiylghw9EfQq/KJhLpYzW9DKE4GAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T01:07:37.367475Z","bundle_sha256":"745d4d89718aa23c1fbfbcb665e473d6005aac442f3712f8b9f55e5bbde1666c"}}