{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TAJSDHOPEBK2NKSE26PZW33ZAP","short_pith_number":"pith:TAJSDHOP","canonical_record":{"source":{"id":"2402.00179","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-31T21:14:01Z","cross_cats_sorted":[],"title_canon_sha256":"34e06010436437a7378d6197543a5e0c3b81041e27dd3d59a0546673fcf422b8","abstract_canon_sha256":"6c9cd865286c2737b602d38827ca6d20f1b2654f0bcf94d09d5a9a88bb6d242e"},"schema_version":"1.0"},"canonical_sha256":"9813219dcf2055a6aa44d79f9b6f7903e475c1cdd7d596c10b70c914c4260d90","source":{"kind":"arxiv","id":"2402.00179","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.00179","created_at":"2026-07-05T10:23:18Z"},{"alias_kind":"arxiv_version","alias_value":"2402.00179v2","created_at":"2026-07-05T10:23:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.00179","created_at":"2026-07-05T10:23:18Z"},{"alias_kind":"pith_short_12","alias_value":"TAJSDHOPEBK2","created_at":"2026-07-05T10:23:18Z"},{"alias_kind":"pith_short_16","alias_value":"TAJSDHOPEBK2NKSE","created_at":"2026-07-05T10:23:18Z"},{"alias_kind":"pith_short_8","alias_value":"TAJSDHOP","created_at":"2026-07-05T10:23:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TAJSDHOPEBK2NKSE26PZW33ZAP","target":"record","payload":{"canonical_record":{"source":{"id":"2402.00179","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-31T21:14:01Z","cross_cats_sorted":[],"title_canon_sha256":"34e06010436437a7378d6197543a5e0c3b81041e27dd3d59a0546673fcf422b8","abstract_canon_sha256":"6c9cd865286c2737b602d38827ca6d20f1b2654f0bcf94d09d5a9a88bb6d242e"},"schema_version":"1.0"},"canonical_sha256":"9813219dcf2055a6aa44d79f9b6f7903e475c1cdd7d596c10b70c914c4260d90","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:23:18.290267Z","signature_b64":"bcUr/Lm3SYkqH1hGLs08CGultpOU9LMYpQpSdeEn2dSDihbUyLBOugw9fANT0zmiEdrwvo3QLRugF5xvK8vVAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9813219dcf2055a6aa44d79f9b6f7903e475c1cdd7d596c10b70c914c4260d90","last_reissued_at":"2026-07-05T10:23:18.289675Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:23:18.289675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.00179","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:23:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3sn3fi5vpw7QMPWFKsQrBO+wzJjcetkKHGOTFPGCC/YgERSlpROg2Oi1FYCNz9GEZhe6NmcUdVs+hDd77n5CDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:06:07.254094Z"},"content_sha256":"8cfee18ef946a2d1a5b04489e595f4235897a0d06b48b644e917008e2af11759","schema_version":"1.0","event_id":"sha256:8cfee18ef946a2d1a5b04489e595f4235897a0d06b48b644e917008e2af11759"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TAJSDHOPEBK2NKSE26PZW33ZAP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"De-identification is not enough: a comparison between de-identified and synthetic clinical notes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Atiquer Rahman Sarkar, Noman Mohammed, Xiaoqian Jiang, Yao-Shun Chuang","submitted_at":"2024-01-31T21:14:01Z","abstract_excerpt":"For sharing privacy-sensitive data, de-identification is commonly regarded as adequate for safeguarding privacy. Synthetic data is also being considered as a privacy-preserving alternative. Recent successes with numerical and tabular data generative models and the breakthroughs in large generative language models raise the question of whether synthetically generated clinical notes could be a viable alternative to real notes for research purposes. In this work, we demonstrated that (i) de-identification of real clinical notes does not protect records against a membership inference attack, (ii) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.00179","kind":"arxiv","version":2},"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/2402.00179/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":"2026-07-05T10:23:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S4KNmXbRAraPH8/9Ol2WWJlBMnLxGg+0ltEyS2l4HcYla7wtZA3wp4cvd7J4SfRrOQyPJOED6avMrUHIddhbCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:06:07.254699Z"},"content_sha256":"94744c6e3ff9c92f8c32206fe23fbe32739f5539a6f76020a9e0abe04d60fb37","schema_version":"1.0","event_id":"sha256:94744c6e3ff9c92f8c32206fe23fbe32739f5539a6f76020a9e0abe04d60fb37"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TAJSDHOPEBK2NKSE26PZW33ZAP/bundle.json","state_url":"https://pith.science/pith/TAJSDHOPEBK2NKSE26PZW33ZAP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TAJSDHOPEBK2NKSE26PZW33ZAP/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":"2026-08-08T11:06:07Z","links":{"resolver":"https://pith.science/pith/TAJSDHOPEBK2NKSE26PZW33ZAP","bundle":"https://pith.science/pith/TAJSDHOPEBK2NKSE26PZW33ZAP/bundle.json","state":"https://pith.science/pith/TAJSDHOPEBK2NKSE26PZW33ZAP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TAJSDHOPEBK2NKSE26PZW33ZAP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TAJSDHOPEBK2NKSE26PZW33ZAP","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":"6c9cd865286c2737b602d38827ca6d20f1b2654f0bcf94d09d5a9a88bb6d242e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-31T21:14:01Z","title_canon_sha256":"34e06010436437a7378d6197543a5e0c3b81041e27dd3d59a0546673fcf422b8"},"schema_version":"1.0","source":{"id":"2402.00179","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.00179","created_at":"2026-07-05T10:23:18Z"},{"alias_kind":"arxiv_version","alias_value":"2402.00179v2","created_at":"2026-07-05T10:23:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.00179","created_at":"2026-07-05T10:23:18Z"},{"alias_kind":"pith_short_12","alias_value":"TAJSDHOPEBK2","created_at":"2026-07-05T10:23:18Z"},{"alias_kind":"pith_short_16","alias_value":"TAJSDHOPEBK2NKSE","created_at":"2026-07-05T10:23:18Z"},{"alias_kind":"pith_short_8","alias_value":"TAJSDHOP","created_at":"2026-07-05T10:23:18Z"}],"graph_snapshots":[{"event_id":"sha256:94744c6e3ff9c92f8c32206fe23fbe32739f5539a6f76020a9e0abe04d60fb37","target":"graph","created_at":"2026-07-05T10:23:18Z","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/2402.00179/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"For sharing privacy-sensitive data, de-identification is commonly regarded as adequate for safeguarding privacy. Synthetic data is also being considered as a privacy-preserving alternative. Recent successes with numerical and tabular data generative models and the breakthroughs in large generative language models raise the question of whether synthetically generated clinical notes could be a viable alternative to real notes for research purposes. In this work, we demonstrated that (i) de-identification of real clinical notes does not protect records against a membership inference attack, (ii) ","authors_text":"Atiquer Rahman Sarkar, Noman Mohammed, Xiaoqian Jiang, Yao-Shun Chuang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-31T21:14:01Z","title":"De-identification is not enough: a comparison between de-identified and synthetic clinical notes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.00179","kind":"arxiv","version":2},"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":"sha256:8cfee18ef946a2d1a5b04489e595f4235897a0d06b48b644e917008e2af11759","target":"record","created_at":"2026-07-05T10:23:18Z","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":"6c9cd865286c2737b602d38827ca6d20f1b2654f0bcf94d09d5a9a88bb6d242e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-31T21:14:01Z","title_canon_sha256":"34e06010436437a7378d6197543a5e0c3b81041e27dd3d59a0546673fcf422b8"},"schema_version":"1.0","source":{"id":"2402.00179","kind":"arxiv","version":2}},"canonical_sha256":"9813219dcf2055a6aa44d79f9b6f7903e475c1cdd7d596c10b70c914c4260d90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9813219dcf2055a6aa44d79f9b6f7903e475c1cdd7d596c10b70c914c4260d90","first_computed_at":"2026-07-05T10:23:18.289675Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:23:18.289675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bcUr/Lm3SYkqH1hGLs08CGultpOU9LMYpQpSdeEn2dSDihbUyLBOugw9fANT0zmiEdrwvo3QLRugF5xvK8vVAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:23:18.290267Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.00179","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8cfee18ef946a2d1a5b04489e595f4235897a0d06b48b644e917008e2af11759","sha256:94744c6e3ff9c92f8c32206fe23fbe32739f5539a6f76020a9e0abe04d60fb37"],"state_sha256":"ab05624ba31cd214d058a9ca01627736973f5ff807a291e9fb3b365a76007640"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b5bX9ClJbDVxLCguztyuy8WE97DmT+4TguVu8oLJUJavqsdrB+ud3YFjcPj9x/fBFsTxFNRX403MKgeF6CCuDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:06:07.260344Z","bundle_sha256":"22474c11475da54d2409dbdcd6bfdfeb838c15141f9ff60747faa77933e6687d"}}