{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:LBMRNARFKIRDJ6K732BNIV2FP4","short_pith_number":"pith:LBMRNARF","canonical_record":{"source":{"id":"1803.02728","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-07T15:51:11Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"43a71cc4ab38fa2cc55be8461d6bec546edb415e4041754dafd4b49917d055c1","abstract_canon_sha256":"98a887bee06d1afa3b921b941930901fb996fb5dee855b85894ded093d887372"},"schema_version":"1.0"},"canonical_sha256":"5859168225522234f95fde82d457457f3b91dd1d632c141afe6f59f6ba15ce91","source":{"kind":"arxiv","id":"1803.02728","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.02728","created_at":"2026-05-18T00:21:49Z"},{"alias_kind":"arxiv_version","alias_value":"1803.02728v1","created_at":"2026-05-18T00:21:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.02728","created_at":"2026-05-18T00:21:49Z"},{"alias_kind":"pith_short_12","alias_value":"LBMRNARFKIRD","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"LBMRNARFKIRDJ6K7","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"LBMRNARF","created_at":"2026-05-18T12:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:LBMRNARFKIRDJ6K732BNIV2FP4","target":"record","payload":{"canonical_record":{"source":{"id":"1803.02728","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-07T15:51:11Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"43a71cc4ab38fa2cc55be8461d6bec546edb415e4041754dafd4b49917d055c1","abstract_canon_sha256":"98a887bee06d1afa3b921b941930901fb996fb5dee855b85894ded093d887372"},"schema_version":"1.0"},"canonical_sha256":"5859168225522234f95fde82d457457f3b91dd1d632c141afe6f59f6ba15ce91","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:21:49.402942Z","signature_b64":"2mAZn+3QigjszJfhzdZ9SljethZxMkezMoCQ3QcuPqBMKZxpLLTeN0o5tzB/mZnoqOxSNQmvj72xalhmW2aZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5859168225522234f95fde82d457457f3b91dd1d632c141afe6f59f6ba15ce91","last_reissued_at":"2026-05-18T00:21:49.402289Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:21:49.402289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.02728","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":"2026-05-18T00:21:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QvBWqI5LBCQ30QvQHABOGpe+LIm284pvLB9mM8nrr/PSXJtf3W1eGWC/QUBuvh8Fed44O356mta1IGGCWmFsAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T17:31:07.568011Z"},"content_sha256":"f731a07c9f2aa19dfaf7e1bdefb416f65813968ab4c4b497831501c15869b218","schema_version":"1.0","event_id":"sha256:f731a07c9f2aa19dfaf7e1bdefb416f65813968ab4c4b497831501c15869b218"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:LBMRNARFKIRDJ6K732BNIV2FP4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards the Creation of a Large Corpus of Synthetically-Identified Clinical Notes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Peter Szolovits, Tristan Naumann, Willie Boag","submitted_at":"2018-03-07T15:51:11Z","abstract_excerpt":"Clinical notes often describe the most important aspects of a patient's physiology and are therefore critical to medical research. However, these notes are typically inaccessible to researchers without prior removal of sensitive protected health information (PHI), a natural language processing (NLP) task referred to as deidentification. Tools to automatically de-identify clinical notes are needed but are difficult to create without access to those very same notes containing PHI. This work presents a first step toward creating a large synthetically-identified corpus of clinical notes and corres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.02728","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":"2026-05-18T00:21:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MvaWNEn8iCB8ybaWV6vJx3uvwME3fJsJdgLI+h01JR88A378o3qilEKHaklF37IJ50C2+dRsFUGkQ3EcnlsUDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T17:31:07.568392Z"},"content_sha256":"3d0d0aee51049750f012ecfa5f1516caf4cc95e9db60f7e8ba5a4d4bbabd4ed6","schema_version":"1.0","event_id":"sha256:3d0d0aee51049750f012ecfa5f1516caf4cc95e9db60f7e8ba5a4d4bbabd4ed6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LBMRNARFKIRDJ6K732BNIV2FP4/bundle.json","state_url":"https://pith.science/pith/LBMRNARFKIRDJ6K732BNIV2FP4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LBMRNARFKIRDJ6K732BNIV2FP4/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":"2026-06-01T17:31:07Z","links":{"resolver":"https://pith.science/pith/LBMRNARFKIRDJ6K732BNIV2FP4","bundle":"https://pith.science/pith/LBMRNARFKIRDJ6K732BNIV2FP4/bundle.json","state":"https://pith.science/pith/LBMRNARFKIRDJ6K732BNIV2FP4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LBMRNARFKIRDJ6K732BNIV2FP4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:LBMRNARFKIRDJ6K732BNIV2FP4","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":"98a887bee06d1afa3b921b941930901fb996fb5dee855b85894ded093d887372","cross_cats_sorted":["cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-07T15:51:11Z","title_canon_sha256":"43a71cc4ab38fa2cc55be8461d6bec546edb415e4041754dafd4b49917d055c1"},"schema_version":"1.0","source":{"id":"1803.02728","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.02728","created_at":"2026-05-18T00:21:49Z"},{"alias_kind":"arxiv_version","alias_value":"1803.02728v1","created_at":"2026-05-18T00:21:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.02728","created_at":"2026-05-18T00:21:49Z"},{"alias_kind":"pith_short_12","alias_value":"LBMRNARFKIRD","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"LBMRNARFKIRDJ6K7","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"LBMRNARF","created_at":"2026-05-18T12:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:3d0d0aee51049750f012ecfa5f1516caf4cc95e9db60f7e8ba5a4d4bbabd4ed6","target":"graph","created_at":"2026-05-18T00:21:49Z","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":"Clinical notes often describe the most important aspects of a patient's physiology and are therefore critical to medical research. However, these notes are typically inaccessible to researchers without prior removal of sensitive protected health information (PHI), a natural language processing (NLP) task referred to as deidentification. Tools to automatically de-identify clinical notes are needed but are difficult to create without access to those very same notes containing PHI. This work presents a first step toward creating a large synthetically-identified corpus of clinical notes and corres","authors_text":"Peter Szolovits, Tristan Naumann, Willie Boag","cross_cats":["cs.CY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-07T15:51:11Z","title":"Towards the Creation of a Large Corpus of Synthetically-Identified Clinical Notes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.02728","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:f731a07c9f2aa19dfaf7e1bdefb416f65813968ab4c4b497831501c15869b218","target":"record","created_at":"2026-05-18T00:21:49Z","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":"98a887bee06d1afa3b921b941930901fb996fb5dee855b85894ded093d887372","cross_cats_sorted":["cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-07T15:51:11Z","title_canon_sha256":"43a71cc4ab38fa2cc55be8461d6bec546edb415e4041754dafd4b49917d055c1"},"schema_version":"1.0","source":{"id":"1803.02728","kind":"arxiv","version":1}},"canonical_sha256":"5859168225522234f95fde82d457457f3b91dd1d632c141afe6f59f6ba15ce91","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5859168225522234f95fde82d457457f3b91dd1d632c141afe6f59f6ba15ce91","first_computed_at":"2026-05-18T00:21:49.402289Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:21:49.402289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2mAZn+3QigjszJfhzdZ9SljethZxMkezMoCQ3QcuPqBMKZxpLLTeN0o5tzB/mZnoqOxSNQmvj72xalhmW2aZDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:21:49.402942Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.02728","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f731a07c9f2aa19dfaf7e1bdefb416f65813968ab4c4b497831501c15869b218","sha256:3d0d0aee51049750f012ecfa5f1516caf4cc95e9db60f7e8ba5a4d4bbabd4ed6"],"state_sha256":"326bb5b8a0838571df9436e8d0143ae63b4ec2e56022e862ded0310bd51023c7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"np/u9fQs0MO85R3sifKvP/tKu7FMN0Nin9dADVrDC04OY4CseZG/N6g7XIxAAF8u1kR9UlPxWRE8/7n5y346Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T17:31:07.570452Z","bundle_sha256":"865337ff76bef5a91932a2721de9d96c93278faa590733ba3e099106ab9387dd"}}