{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:TJWXRKZJNGZCRMIQ7G3VH2ZLQF","short_pith_number":"pith:TJWXRKZJ","canonical_record":{"source":{"id":"1908.05596","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-08-14T14:06:11Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"268732bf8d0cec7f4b2add14eb161f94ab676c1db62389d90f1af40397321437","abstract_canon_sha256":"a5e93b9baf7c0054f215996f30b83e4e97f48f41a03b5689c580b168b0adbdc6"},"schema_version":"1.0"},"canonical_sha256":"9a6d78ab2969b228b110f9b753eb2b815dd6cb010cff19987adeb2518e8818c9","source":{"kind":"arxiv","id":"1908.05596","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.05596","created_at":"2026-07-04T23:56:54Z"},{"alias_kind":"arxiv_version","alias_value":"1908.05596v1","created_at":"2026-07-04T23:56:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05596","created_at":"2026-07-04T23:56:54Z"},{"alias_kind":"pith_short_12","alias_value":"TJWXRKZJNGZC","created_at":"2026-07-04T23:56:54Z"},{"alias_kind":"pith_short_16","alias_value":"TJWXRKZJNGZCRMIQ","created_at":"2026-07-04T23:56:54Z"},{"alias_kind":"pith_short_8","alias_value":"TJWXRKZJ","created_at":"2026-07-04T23:56:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:TJWXRKZJNGZCRMIQ7G3VH2ZLQF","target":"record","payload":{"canonical_record":{"source":{"id":"1908.05596","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-08-14T14:06:11Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"268732bf8d0cec7f4b2add14eb161f94ab676c1db62389d90f1af40397321437","abstract_canon_sha256":"a5e93b9baf7c0054f215996f30b83e4e97f48f41a03b5689c580b168b0adbdc6"},"schema_version":"1.0"},"canonical_sha256":"9a6d78ab2969b228b110f9b753eb2b815dd6cb010cff19987adeb2518e8818c9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:56:54.132047Z","signature_b64":"OpItomIYL/mmbqIPCPX4S0ZJxzlG0/X8ztI1Y964kxWjn8Q/YLcEOcn8adaniXCVRrli1+MLEYcTosXaBqp0CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a6d78ab2969b228b110f9b753eb2b815dd6cb010cff19987adeb2518e8818c9","last_reissued_at":"2026-07-04T23:56:54.131652Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:56:54.131652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.05596","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":"2026-07-04T23:56:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MX4iRb8L8sMhXQGX+qShejamJT+z0rHPmub21JLJ2SGN2054al+pWUTxH83jQSvzzLnbrFG6P5ZHvHReFQGSBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T19:24:17.409140Z"},"content_sha256":"134f81e2682f94afc23eb23b21063f306a87e2fa87ebd148081860a55c5e8f8c","schema_version":"1.0","event_id":"sha256:134f81e2682f94afc23eb23b21063f306a87e2fa87ebd148081860a55c5e8f8c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:TJWXRKZJNGZCRMIQ7G3VH2ZLQF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Two-stage Federated Phenotyping and Patient Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Dianbo Liu, Dmitriy Dligach, Timothy Miller","submitted_at":"2019-08-14T14:06:11Z","abstract_excerpt":"A large percentage of medical information is in unstructured text format in electronic medical record systems. Manual extraction of information from clinical notes is extremely time consuming. Natural language processing has been widely used in recent years for automatic information extraction from medical texts. However, algorithms trained on data from a single healthcare provider are not generalizable and error-prone due to the heterogeneity and uniqueness of medical documents. We develop a two-stage federated natural language processing method that enables utilization of clinical notes from"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.05596","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/1908.05596/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":"2026-07-04T23:56:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YIcZpP93FJIgWethw/ov6QFPAjjZXEPDqRdYf2edD8UCK2D7qaz96/hYunI70HU9UwVmOiuaX6jNnEwruOcrAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T19:24:17.409660Z"},"content_sha256":"1deccb3d040b106dbd59450cc0cad2f6b406e85a5e30358a514b6f7598b3f7b8","schema_version":"1.0","event_id":"sha256:1deccb3d040b106dbd59450cc0cad2f6b406e85a5e30358a514b6f7598b3f7b8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TJWXRKZJNGZCRMIQ7G3VH2ZLQF/bundle.json","state_url":"https://pith.science/pith/TJWXRKZJNGZCRMIQ7G3VH2ZLQF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TJWXRKZJNGZCRMIQ7G3VH2ZLQF/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":"2026-08-21T19:24:17Z","links":{"resolver":"https://pith.science/pith/TJWXRKZJNGZCRMIQ7G3VH2ZLQF","bundle":"https://pith.science/pith/TJWXRKZJNGZCRMIQ7G3VH2ZLQF/bundle.json","state":"https://pith.science/pith/TJWXRKZJNGZCRMIQ7G3VH2ZLQF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TJWXRKZJNGZCRMIQ7G3VH2ZLQF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:TJWXRKZJNGZCRMIQ7G3VH2ZLQF","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":"a5e93b9baf7c0054f215996f30b83e4e97f48f41a03b5689c580b168b0adbdc6","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-08-14T14:06:11Z","title_canon_sha256":"268732bf8d0cec7f4b2add14eb161f94ab676c1db62389d90f1af40397321437"},"schema_version":"1.0","source":{"id":"1908.05596","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.05596","created_at":"2026-07-04T23:56:54Z"},{"alias_kind":"arxiv_version","alias_value":"1908.05596v1","created_at":"2026-07-04T23:56:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05596","created_at":"2026-07-04T23:56:54Z"},{"alias_kind":"pith_short_12","alias_value":"TJWXRKZJNGZC","created_at":"2026-07-04T23:56:54Z"},{"alias_kind":"pith_short_16","alias_value":"TJWXRKZJNGZCRMIQ","created_at":"2026-07-04T23:56:54Z"},{"alias_kind":"pith_short_8","alias_value":"TJWXRKZJ","created_at":"2026-07-04T23:56:54Z"}],"graph_snapshots":[{"event_id":"sha256:1deccb3d040b106dbd59450cc0cad2f6b406e85a5e30358a514b6f7598b3f7b8","target":"graph","created_at":"2026-07-04T23:56:54Z","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/1908.05596/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A large percentage of medical information is in unstructured text format in electronic medical record systems. Manual extraction of information from clinical notes is extremely time consuming. Natural language processing has been widely used in recent years for automatic information extraction from medical texts. However, algorithms trained on data from a single healthcare provider are not generalizable and error-prone due to the heterogeneity and uniqueness of medical documents. We develop a two-stage federated natural language processing method that enables utilization of clinical notes from","authors_text":"Dianbo Liu, Dmitriy Dligach, Timothy Miller","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-08-14T14:06:11Z","title":"Two-stage Federated Phenotyping and Patient Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.05596","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":"sha256:134f81e2682f94afc23eb23b21063f306a87e2fa87ebd148081860a55c5e8f8c","target":"record","created_at":"2026-07-04T23:56:54Z","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":"a5e93b9baf7c0054f215996f30b83e4e97f48f41a03b5689c580b168b0adbdc6","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-08-14T14:06:11Z","title_canon_sha256":"268732bf8d0cec7f4b2add14eb161f94ab676c1db62389d90f1af40397321437"},"schema_version":"1.0","source":{"id":"1908.05596","kind":"arxiv","version":1}},"canonical_sha256":"9a6d78ab2969b228b110f9b753eb2b815dd6cb010cff19987adeb2518e8818c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a6d78ab2969b228b110f9b753eb2b815dd6cb010cff19987adeb2518e8818c9","first_computed_at":"2026-07-04T23:56:54.131652Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:56:54.131652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OpItomIYL/mmbqIPCPX4S0ZJxzlG0/X8ztI1Y964kxWjn8Q/YLcEOcn8adaniXCVRrli1+MLEYcTosXaBqp0CA==","signature_status":"signed_v1","signed_at":"2026-07-04T23:56:54.132047Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.05596","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:134f81e2682f94afc23eb23b21063f306a87e2fa87ebd148081860a55c5e8f8c","sha256:1deccb3d040b106dbd59450cc0cad2f6b406e85a5e30358a514b6f7598b3f7b8"],"state_sha256":"07d11515dc9384bd022185edb72b0bd8fa88f02efed64da37ad9c926f1751f49"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZkTYdlKURkWUTz8soCybbFOBIwa3eZ+/p0JSTM8BCdXIw36BvxBt2EsSD+8+hYdk1ASGznNL/9h/fvxOnmCXDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T19:24:17.414180Z","bundle_sha256":"284d17786f621c280ea6b98f446fc0363af390ecb6c66fd5274a5fd6cacaf2dc"}}