{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:7WWCQFIXWFBLCHTFF4BYLDRGWI","short_pith_number":"pith:7WWCQFIX","canonical_record":{"source":{"id":"1906.03380","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-08T03:32:00Z","cross_cats_sorted":[],"title_canon_sha256":"acc3148518cee85086c19ae06264154a10335344261c39f17fe7b7e52470fc43","abstract_canon_sha256":"096773afd5ba459ed9e08ea51cd9f309fb5cd3665a30ca167be49aa69ea7e1cc"},"schema_version":"1.0"},"canonical_sha256":"fdac281517b142b11e652f03858e26b2303f121d9b5238abb23f8a332d0cd352","source":{"kind":"arxiv","id":"1906.03380","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.03380","created_at":"2026-05-17T23:43:48Z"},{"alias_kind":"arxiv_version","alias_value":"1906.03380v1","created_at":"2026-05-17T23:43:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03380","created_at":"2026-05-17T23:43:48Z"},{"alias_kind":"pith_short_12","alias_value":"7WWCQFIXWFBL","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"7WWCQFIXWFBLCHTF","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"7WWCQFIX","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:7WWCQFIXWFBLCHTFF4BYLDRGWI","target":"record","payload":{"canonical_record":{"source":{"id":"1906.03380","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-08T03:32:00Z","cross_cats_sorted":[],"title_canon_sha256":"acc3148518cee85086c19ae06264154a10335344261c39f17fe7b7e52470fc43","abstract_canon_sha256":"096773afd5ba459ed9e08ea51cd9f309fb5cd3665a30ca167be49aa69ea7e1cc"},"schema_version":"1.0"},"canonical_sha256":"fdac281517b142b11e652f03858e26b2303f121d9b5238abb23f8a332d0cd352","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:48.654439Z","signature_b64":"JA1Kdc/ZfpslZtLoayafRGSSCU2XKx2Lr5Ij+Bbz8OXSMN4cvBivTcv4vbhYY4MRMbcYegyvOrH126lIwLjEDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdac281517b142b11e652f03858e26b2303f121d9b5238abb23f8a332d0cd352","last_reissued_at":"2026-05-17T23:43:48.653732Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:48.653732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.03380","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":"2026-05-17T23:43:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lnqPaviJ361HngZFMW1b8IUxAS6+nNLlROk8W4wMrcwm0lGdEJP9MKsRFW4AWFdq2O8z1ogH3Fe6L9l9dETSDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T23:35:56.820810Z"},"content_sha256":"948161cc398f471f662ac8c14bf0bdd6064f1f332265886bd9a18033901bbf51","schema_version":"1.0","event_id":"sha256:948161cc398f471f662ac8c14bf0bdd6064f1f332265886bd9a18033901bbf51"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:7WWCQFIXWFBLCHTFF4BYLDRGWI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Clinical Concept Extraction for Document-Level Coding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Edward Choi, Jacob Eisenstein, Jimeng Sun, Sarah Wiegreffe, Sherry Yan","submitted_at":"2019-06-08T03:32:00Z","abstract_excerpt":"The text of clinical notes can be a valuable source of patient information and clinical assessments. Historically, the primary approach for exploiting clinical notes has been information extraction: linking spans of text to concepts in a detailed domain ontology. However, recent work has demonstrated the potential of supervised machine learning to extract document-level codes directly from the raw text of clinical notes. We propose to bridge the gap between the two approaches with two novel syntheses: (1) treating extracted concepts as features, which are used to supplement or replace the text"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03380","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":""},"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":"2026-05-17T23:43:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5KJwj4O3ML8OcsFddvyXlN1LTxu6pQXM4BTMPoVIoj722b8iDZsiLSmU2O45w17MU5ahYWTgfb1RDa1tSiiPBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T23:35:56.821451Z"},"content_sha256":"71e2b1f33c003845c36b589b7cd4978277110b16929fda31c9b9d860c0609270","schema_version":"1.0","event_id":"sha256:71e2b1f33c003845c36b589b7cd4978277110b16929fda31c9b9d860c0609270"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7WWCQFIXWFBLCHTFF4BYLDRGWI/bundle.json","state_url":"https://pith.science/pith/7WWCQFIXWFBLCHTFF4BYLDRGWI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7WWCQFIXWFBLCHTFF4BYLDRGWI/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":"2026-05-28T23:35:56Z","links":{"resolver":"https://pith.science/pith/7WWCQFIXWFBLCHTFF4BYLDRGWI","bundle":"https://pith.science/pith/7WWCQFIXWFBLCHTFF4BYLDRGWI/bundle.json","state":"https://pith.science/pith/7WWCQFIXWFBLCHTFF4BYLDRGWI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7WWCQFIXWFBLCHTFF4BYLDRGWI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:7WWCQFIXWFBLCHTFF4BYLDRGWI","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":"096773afd5ba459ed9e08ea51cd9f309fb5cd3665a30ca167be49aa69ea7e1cc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-08T03:32:00Z","title_canon_sha256":"acc3148518cee85086c19ae06264154a10335344261c39f17fe7b7e52470fc43"},"schema_version":"1.0","source":{"id":"1906.03380","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.03380","created_at":"2026-05-17T23:43:48Z"},{"alias_kind":"arxiv_version","alias_value":"1906.03380v1","created_at":"2026-05-17T23:43:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03380","created_at":"2026-05-17T23:43:48Z"},{"alias_kind":"pith_short_12","alias_value":"7WWCQFIXWFBL","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"7WWCQFIXWFBLCHTF","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"7WWCQFIX","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:71e2b1f33c003845c36b589b7cd4978277110b16929fda31c9b9d860c0609270","target":"graph","created_at":"2026-05-17T23:43:48Z","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"},"paper":{"abstract_excerpt":"The text of clinical notes can be a valuable source of patient information and clinical assessments. Historically, the primary approach for exploiting clinical notes has been information extraction: linking spans of text to concepts in a detailed domain ontology. However, recent work has demonstrated the potential of supervised machine learning to extract document-level codes directly from the raw text of clinical notes. We propose to bridge the gap between the two approaches with two novel syntheses: (1) treating extracted concepts as features, which are used to supplement or replace the text","authors_text":"Edward Choi, Jacob Eisenstein, Jimeng Sun, Sarah Wiegreffe, Sherry Yan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-08T03:32:00Z","title":"Clinical Concept Extraction for Document-Level Coding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03380","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":"sha256:948161cc398f471f662ac8c14bf0bdd6064f1f332265886bd9a18033901bbf51","target":"record","created_at":"2026-05-17T23:43:48Z","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":"096773afd5ba459ed9e08ea51cd9f309fb5cd3665a30ca167be49aa69ea7e1cc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-08T03:32:00Z","title_canon_sha256":"acc3148518cee85086c19ae06264154a10335344261c39f17fe7b7e52470fc43"},"schema_version":"1.0","source":{"id":"1906.03380","kind":"arxiv","version":1}},"canonical_sha256":"fdac281517b142b11e652f03858e26b2303f121d9b5238abb23f8a332d0cd352","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fdac281517b142b11e652f03858e26b2303f121d9b5238abb23f8a332d0cd352","first_computed_at":"2026-05-17T23:43:48.653732Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:48.653732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JA1Kdc/ZfpslZtLoayafRGSSCU2XKx2Lr5Ij+Bbz8OXSMN4cvBivTcv4vbhYY4MRMbcYegyvOrH126lIwLjEDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:48.654439Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.03380","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:948161cc398f471f662ac8c14bf0bdd6064f1f332265886bd9a18033901bbf51","sha256:71e2b1f33c003845c36b589b7cd4978277110b16929fda31c9b9d860c0609270"],"state_sha256":"bd1ee6deb79082fbc8f59849a964d47be00adfb753d293c6047181314cac06df"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CzDws0qRVwUqIhyQSlRi8salEX9XdG8UO30p+S7TKIKiLugT5xfNgtVm/C4WAEB1AUaN68OTAmBNCKyCnovtBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T23:35:56.825116Z","bundle_sha256":"62ab7bb478ff9edd510baccb087d78691b17170503649eafb46fdfd72273dfae"}}