{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:DLG2IVFXII2KSGUEHO3MRFHMBS","short_pith_number":"pith:DLG2IVFX","canonical_record":{"source":{"id":"2101.00146","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-01T03:09:31Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"4b2698867d8dd14f5310fa0f3eee3d94652fca21554fe645b75e50025c0a7a6c","abstract_canon_sha256":"3a00d829bc44d3dc08dc99777c86ea64a44d2b7ed5d99e2b48be25cb2648c5e3"},"schema_version":"1.0"},"canonical_sha256":"1acda454b74234a91a843bb6c894ec0c8117b6b1df82bb0dc1dd280b95f42156","source":{"kind":"arxiv","id":"2101.00146","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.00146","created_at":"2026-07-05T05:02:52Z"},{"alias_kind":"arxiv_version","alias_value":"2101.00146v4","created_at":"2026-07-05T05:02:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.00146","created_at":"2026-07-05T05:02:52Z"},{"alias_kind":"pith_short_12","alias_value":"DLG2IVFXII2K","created_at":"2026-07-05T05:02:52Z"},{"alias_kind":"pith_short_16","alias_value":"DLG2IVFXII2KSGUE","created_at":"2026-07-05T05:02:52Z"},{"alias_kind":"pith_short_8","alias_value":"DLG2IVFX","created_at":"2026-07-05T05:02:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:DLG2IVFXII2KSGUEHO3MRFHMBS","target":"record","payload":{"canonical_record":{"source":{"id":"2101.00146","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-01T03:09:31Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"4b2698867d8dd14f5310fa0f3eee3d94652fca21554fe645b75e50025c0a7a6c","abstract_canon_sha256":"3a00d829bc44d3dc08dc99777c86ea64a44d2b7ed5d99e2b48be25cb2648c5e3"},"schema_version":"1.0"},"canonical_sha256":"1acda454b74234a91a843bb6c894ec0c8117b6b1df82bb0dc1dd280b95f42156","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:02:52.291603Z","signature_b64":"3dZsFbx81srrRAwSLBB7DvTYQMeJ91LKO7vrPm+lzrWaDaiLMhegN+atrca4xGTy4Vux1KF6GQ8K/unyNPaQBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1acda454b74234a91a843bb6c894ec0c8117b6b1df82bb0dc1dd280b95f42156","last_reissued_at":"2026-07-05T05:02:52.291221Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:02:52.291221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2101.00146","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:02:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k4EMgJiAmbBaYqen/7bN3By0q8E4weNd6cL9tgY7mZ2n8yppUKAPIKlleaonge04+WKGNL9qe67dnEgmE8HoDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T20:06:10.983818Z"},"content_sha256":"6ada8335c854eee929dbce4dc3e205d6899c0a69984c22829f78e12a68185154","schema_version":"1.0","event_id":"sha256:6ada8335c854eee929dbce4dc3e205d6899c0a69984c22829f78e12a68185154"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:DLG2IVFXII2KSGUEHO3MRFHMBS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"De-identifying Australian Hospital Discharge Summaries: An End-to-End Framework using Ensemble of Deep Learning Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Anthony Nguyen, Leibo Liu, Louisa Jorm, Oscar Perez-Concha, Vicki Bennett","submitted_at":"2021-01-01T03:09:31Z","abstract_excerpt":"Electronic Medical Records (EMRs) contain clinical narrative text that is of great potential value to medical researchers. However, this information is mixed with Personally Identifiable Information (PII) that presents risks to patient and clinician confidentiality. This paper presents an end-to-end deidentification framework to automatically remove PII from Australian hospital discharge summaries. Our corpus included 600 hospital discharge summaries which were extracted from the EMRs of two principal referral hospitals in Sydney, Australia. Our end-to-end de-identification framework consists "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.00146","kind":"arxiv","version":4},"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/2101.00146/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":"2026-07-05T05:02:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GW0Ml11XzKs2ZX8YrxibIkBEhZR0iA1RsgOQegiqmf3j5MUzqjYOKEyHPxNtsG+Gclv4m43J0T6QbbxXrfGnCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T20:06:10.984188Z"},"content_sha256":"525ed9142e431296f4f7b84c57c09d0e06eb334f4d6503182fa4c01c65b5e269","schema_version":"1.0","event_id":"sha256:525ed9142e431296f4f7b84c57c09d0e06eb334f4d6503182fa4c01c65b5e269"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DLG2IVFXII2KSGUEHO3MRFHMBS/bundle.json","state_url":"https://pith.science/pith/DLG2IVFXII2KSGUEHO3MRFHMBS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DLG2IVFXII2KSGUEHO3MRFHMBS/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":"2026-07-08T20:06:10Z","links":{"resolver":"https://pith.science/pith/DLG2IVFXII2KSGUEHO3MRFHMBS","bundle":"https://pith.science/pith/DLG2IVFXII2KSGUEHO3MRFHMBS/bundle.json","state":"https://pith.science/pith/DLG2IVFXII2KSGUEHO3MRFHMBS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DLG2IVFXII2KSGUEHO3MRFHMBS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:DLG2IVFXII2KSGUEHO3MRFHMBS","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":"3a00d829bc44d3dc08dc99777c86ea64a44d2b7ed5d99e2b48be25cb2648c5e3","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-01T03:09:31Z","title_canon_sha256":"4b2698867d8dd14f5310fa0f3eee3d94652fca21554fe645b75e50025c0a7a6c"},"schema_version":"1.0","source":{"id":"2101.00146","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.00146","created_at":"2026-07-05T05:02:52Z"},{"alias_kind":"arxiv_version","alias_value":"2101.00146v4","created_at":"2026-07-05T05:02:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.00146","created_at":"2026-07-05T05:02:52Z"},{"alias_kind":"pith_short_12","alias_value":"DLG2IVFXII2K","created_at":"2026-07-05T05:02:52Z"},{"alias_kind":"pith_short_16","alias_value":"DLG2IVFXII2KSGUE","created_at":"2026-07-05T05:02:52Z"},{"alias_kind":"pith_short_8","alias_value":"DLG2IVFX","created_at":"2026-07-05T05:02:52Z"}],"graph_snapshots":[{"event_id":"sha256:525ed9142e431296f4f7b84c57c09d0e06eb334f4d6503182fa4c01c65b5e269","target":"graph","created_at":"2026-07-05T05:02:52Z","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/2101.00146/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Electronic Medical Records (EMRs) contain clinical narrative text that is of great potential value to medical researchers. However, this information is mixed with Personally Identifiable Information (PII) that presents risks to patient and clinician confidentiality. This paper presents an end-to-end deidentification framework to automatically remove PII from Australian hospital discharge summaries. Our corpus included 600 hospital discharge summaries which were extracted from the EMRs of two principal referral hospitals in Sydney, Australia. Our end-to-end de-identification framework consists ","authors_text":"Anthony Nguyen, Leibo Liu, Louisa Jorm, Oscar Perez-Concha, Vicki Bennett","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-01T03:09:31Z","title":"De-identifying Australian Hospital Discharge Summaries: An End-to-End Framework using Ensemble of Deep Learning Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.00146","kind":"arxiv","version":4},"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":"sha256:6ada8335c854eee929dbce4dc3e205d6899c0a69984c22829f78e12a68185154","target":"record","created_at":"2026-07-05T05:02:52Z","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":"3a00d829bc44d3dc08dc99777c86ea64a44d2b7ed5d99e2b48be25cb2648c5e3","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-01T03:09:31Z","title_canon_sha256":"4b2698867d8dd14f5310fa0f3eee3d94652fca21554fe645b75e50025c0a7a6c"},"schema_version":"1.0","source":{"id":"2101.00146","kind":"arxiv","version":4}},"canonical_sha256":"1acda454b74234a91a843bb6c894ec0c8117b6b1df82bb0dc1dd280b95f42156","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1acda454b74234a91a843bb6c894ec0c8117b6b1df82bb0dc1dd280b95f42156","first_computed_at":"2026-07-05T05:02:52.291221Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:02:52.291221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3dZsFbx81srrRAwSLBB7DvTYQMeJ91LKO7vrPm+lzrWaDaiLMhegN+atrca4xGTy4Vux1KF6GQ8K/unyNPaQBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:02:52.291603Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.00146","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ada8335c854eee929dbce4dc3e205d6899c0a69984c22829f78e12a68185154","sha256:525ed9142e431296f4f7b84c57c09d0e06eb334f4d6503182fa4c01c65b5e269"],"state_sha256":"c625bb14c47a1885536fd1d5bed152a9c7180b70ac4d0a20e3be51c4d32e704b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1QQuT8vZT1RKXx6f5JDuqOztPlbyRgktwXaUXWLYsEc7sn7JznAYeFd9yB8/RslwcnDQ18wOAQ9aRJSDKXIBBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T20:06:10.986145Z","bundle_sha256":"0a03056569b7c0e2537d9d9d9152f200c80fa6e6d156875e99e11fb472f81cf5"}}