{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OY34LDWQHTQVJRXAFPJF5GNG74","short_pith_number":"pith:OY34LDWQ","canonical_record":{"source":{"id":"2502.13342","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T23:52:29Z","cross_cats_sorted":[],"title_canon_sha256":"6bf2c3f37c5591ae52e5238451366850b3a226b1398e58f5367fe3398e7d599f","abstract_canon_sha256":"f4c7976db5cc7a9873cd18e221889fc04b54f7d01710e15f577dbde9d524df40"},"schema_version":"1.0"},"canonical_sha256":"7637c58ed03ce154c6e02bd25e99a6ff1f52e985c5f2afa5f63a59cc1d8de382","source":{"kind":"arxiv","id":"2502.13342","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.13342","created_at":"2026-07-05T10:16:45Z"},{"alias_kind":"arxiv_version","alias_value":"2502.13342v1","created_at":"2026-07-05T10:16:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13342","created_at":"2026-07-05T10:16:45Z"},{"alias_kind":"pith_short_12","alias_value":"OY34LDWQHTQV","created_at":"2026-07-05T10:16:45Z"},{"alias_kind":"pith_short_16","alias_value":"OY34LDWQHTQVJRXA","created_at":"2026-07-05T10:16:45Z"},{"alias_kind":"pith_short_8","alias_value":"OY34LDWQ","created_at":"2026-07-05T10:16:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OY34LDWQHTQVJRXAFPJF5GNG74","target":"record","payload":{"canonical_record":{"source":{"id":"2502.13342","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T23:52:29Z","cross_cats_sorted":[],"title_canon_sha256":"6bf2c3f37c5591ae52e5238451366850b3a226b1398e58f5367fe3398e7d599f","abstract_canon_sha256":"f4c7976db5cc7a9873cd18e221889fc04b54f7d01710e15f577dbde9d524df40"},"schema_version":"1.0"},"canonical_sha256":"7637c58ed03ce154c6e02bd25e99a6ff1f52e985c5f2afa5f63a59cc1d8de382","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:45.632909Z","signature_b64":"4RFJE8U4xo2uVPR1YincCPpoSp7WcHXPgRkXNvvie1FwAZt7fEXNB9LyWwg49MYSxxQnMkgU22RDaeHV9LEzBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7637c58ed03ce154c6e02bd25e99a6ff1f52e985c5f2afa5f63a59cc1d8de382","last_reissued_at":"2026-07-05T10:16:45.632467Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:45.632467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.13342","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":"2026-07-05T10:16:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HJvA10orPpP/L3ub1f+ynqdPEbLTjnJCtfeMNw/VPQq8QX6my6DRHYAyetUTGYHtdDG6f/g9IXZQGircu7EFBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T23:37:01.932772Z"},"content_sha256":"36570391a489a7b54c5702ca23e1597f4171cb93c610afcc01ee0af82f9203f2","schema_version":"1.0","event_id":"sha256:36570391a489a7b54c5702ca23e1597f4171cb93c610afcc01ee0af82f9203f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OY34LDWQHTQVJRXAFPJF5GNG74","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond De-Identification: A Structured Approach for Defining and Detecting Indirect Identifiers in Medical Texts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ibrahim Baroud, Lisa Raithel, Roland Roller, Sebastian M\\\"oller","submitted_at":"2025-02-18T23:52:29Z","abstract_excerpt":"Sharing sensitive texts for scientific purposes requires appropriate techniques to protect the privacy of patients and healthcare personnel. Anonymizing textual data is particularly challenging due to the presence of diverse unstructured direct and indirect identifiers. To mitigate the risk of re-identification, this work introduces a schema of nine categories of indirect identifiers designed to account for different potential adversaries, including acquaintances, family members and medical staff. Using this schema, we annotate 100 MIMIC-III discharge summaries and propose baseline models for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13342","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/2502.13342/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":"2026-07-05T10:16:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"swgXAzxlNpI8Ekjs31I6ZewfxmiLEyE+uKxsIvGRMWEdXQOWnDQ178GMDl8xsdZLU1ye/vcabD8NwqxsE3Y5Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T23:37:01.933152Z"},"content_sha256":"1ab0a8b8b03e166508c5b008bebc8ef886d9929b52e3356e24e0b91f9e5594d8","schema_version":"1.0","event_id":"sha256:1ab0a8b8b03e166508c5b008bebc8ef886d9929b52e3356e24e0b91f9e5594d8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OY34LDWQHTQVJRXAFPJF5GNG74/bundle.json","state_url":"https://pith.science/pith/OY34LDWQHTQVJRXAFPJF5GNG74/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OY34LDWQHTQVJRXAFPJF5GNG74/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":"2026-07-08T23:37:01Z","links":{"resolver":"https://pith.science/pith/OY34LDWQHTQVJRXAFPJF5GNG74","bundle":"https://pith.science/pith/OY34LDWQHTQVJRXAFPJF5GNG74/bundle.json","state":"https://pith.science/pith/OY34LDWQHTQVJRXAFPJF5GNG74/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OY34LDWQHTQVJRXAFPJF5GNG74/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OY34LDWQHTQVJRXAFPJF5GNG74","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":"f4c7976db5cc7a9873cd18e221889fc04b54f7d01710e15f577dbde9d524df40","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T23:52:29Z","title_canon_sha256":"6bf2c3f37c5591ae52e5238451366850b3a226b1398e58f5367fe3398e7d599f"},"schema_version":"1.0","source":{"id":"2502.13342","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.13342","created_at":"2026-07-05T10:16:45Z"},{"alias_kind":"arxiv_version","alias_value":"2502.13342v1","created_at":"2026-07-05T10:16:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13342","created_at":"2026-07-05T10:16:45Z"},{"alias_kind":"pith_short_12","alias_value":"OY34LDWQHTQV","created_at":"2026-07-05T10:16:45Z"},{"alias_kind":"pith_short_16","alias_value":"OY34LDWQHTQVJRXA","created_at":"2026-07-05T10:16:45Z"},{"alias_kind":"pith_short_8","alias_value":"OY34LDWQ","created_at":"2026-07-05T10:16:45Z"}],"graph_snapshots":[{"event_id":"sha256:1ab0a8b8b03e166508c5b008bebc8ef886d9929b52e3356e24e0b91f9e5594d8","target":"graph","created_at":"2026-07-05T10:16:45Z","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/2502.13342/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sharing sensitive texts for scientific purposes requires appropriate techniques to protect the privacy of patients and healthcare personnel. Anonymizing textual data is particularly challenging due to the presence of diverse unstructured direct and indirect identifiers. To mitigate the risk of re-identification, this work introduces a schema of nine categories of indirect identifiers designed to account for different potential adversaries, including acquaintances, family members and medical staff. Using this schema, we annotate 100 MIMIC-III discharge summaries and propose baseline models for ","authors_text":"Ibrahim Baroud, Lisa Raithel, Roland Roller, Sebastian M\\\"oller","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T23:52:29Z","title":"Beyond De-Identification: A Structured Approach for Defining and Detecting Indirect Identifiers in Medical Texts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13342","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":"sha256:36570391a489a7b54c5702ca23e1597f4171cb93c610afcc01ee0af82f9203f2","target":"record","created_at":"2026-07-05T10:16:45Z","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":"f4c7976db5cc7a9873cd18e221889fc04b54f7d01710e15f577dbde9d524df40","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T23:52:29Z","title_canon_sha256":"6bf2c3f37c5591ae52e5238451366850b3a226b1398e58f5367fe3398e7d599f"},"schema_version":"1.0","source":{"id":"2502.13342","kind":"arxiv","version":1}},"canonical_sha256":"7637c58ed03ce154c6e02bd25e99a6ff1f52e985c5f2afa5f63a59cc1d8de382","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7637c58ed03ce154c6e02bd25e99a6ff1f52e985c5f2afa5f63a59cc1d8de382","first_computed_at":"2026-07-05T10:16:45.632467Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:16:45.632467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4RFJE8U4xo2uVPR1YincCPpoSp7WcHXPgRkXNvvie1FwAZt7fEXNB9LyWwg49MYSxxQnMkgU22RDaeHV9LEzBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:16:45.632909Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.13342","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36570391a489a7b54c5702ca23e1597f4171cb93c610afcc01ee0af82f9203f2","sha256:1ab0a8b8b03e166508c5b008bebc8ef886d9929b52e3356e24e0b91f9e5594d8"],"state_sha256":"a97129b65e211fad9c6315f9fadbbd26787fa5682577d99a464e936430884c10"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ELqhlQjd84BvoQRbBl4uJNkNz25IIsZjVtwahEx2W3zM18LAdrbUlr4dEK3SH5oh4Hl4bynH4UWi6eaiYMwLAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T23:37:01.935341Z","bundle_sha256":"9f85ee6b0579e6630958f576195522d56d79bc4f4377a508dddf00b020b2c163"}}