{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5RMKWPZVR6B6EZGQ2VCUGZV2KE","short_pith_number":"pith:5RMKWPZV","canonical_record":{"source":{"id":"2310.04468","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-05T19:10:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"419d6f550b5f67ddfe4dec04ac7fa0c223227f724e801caa57e4045e1ae2abc5","abstract_canon_sha256":"71120c66f8e4ec98a5e375c9e82bbcccc6a2dc4f7cfbd19d7d211be5e4f7fabc"},"schema_version":"1.0"},"canonical_sha256":"ec58ab3f358f83e264d0d5454366ba511e9f201b4f99f2cde6384e508428c8fd","source":{"kind":"arxiv","id":"2310.04468","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.04468","created_at":"2026-07-05T06:58:18Z"},{"alias_kind":"arxiv_version","alias_value":"2310.04468v1","created_at":"2026-07-05T06:58:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.04468","created_at":"2026-07-05T06:58:18Z"},{"alias_kind":"pith_short_12","alias_value":"5RMKWPZVR6B6","created_at":"2026-07-05T06:58:18Z"},{"alias_kind":"pith_short_16","alias_value":"5RMKWPZVR6B6EZGQ","created_at":"2026-07-05T06:58:18Z"},{"alias_kind":"pith_short_8","alias_value":"5RMKWPZV","created_at":"2026-07-05T06:58:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5RMKWPZVR6B6EZGQ2VCUGZV2KE","target":"record","payload":{"canonical_record":{"source":{"id":"2310.04468","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-05T19:10:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"419d6f550b5f67ddfe4dec04ac7fa0c223227f724e801caa57e4045e1ae2abc5","abstract_canon_sha256":"71120c66f8e4ec98a5e375c9e82bbcccc6a2dc4f7cfbd19d7d211be5e4f7fabc"},"schema_version":"1.0"},"canonical_sha256":"ec58ab3f358f83e264d0d5454366ba511e9f201b4f99f2cde6384e508428c8fd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:58:18.792517Z","signature_b64":"4EOej3YJy5m9lJgTZPPhCDtNVQUwejPilUdPzwAGwbkUFyOPuKv5Vpal1RwHwaN+UMemn0usjN90FxKVXmFHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec58ab3f358f83e264d0d5454366ba511e9f201b4f99f2cde6384e508428c8fd","last_reissued_at":"2026-07-05T06:58:18.792033Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:58:18.792033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.04468","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":"2026-07-05T06:58:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nuQ4c7CvI9VLbnB/MEXk1Khe/mzg2IIc4fx7tKY/v6fmDRN5jNiHsKB2Z2+aeDHv4yGwX3SvkoVIdnMQLmnRCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T11:01:54.526380Z"},"content_sha256":"8a3af4c1909bce9651d864a5d84dd031fef6831d75e5d06686415d40a328a1d0","schema_version":"1.0","event_id":"sha256:8a3af4c1909bce9651d864a5d84dd031fef6831d75e5d06686415d40a328a1d0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5RMKWPZVR6B6EZGQ2VCUGZV2KE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Validating transformers for redaction of text from electronic health records in real-world healthcare","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anoop D. Shah, Anthony Shek, Ewart Jonathan Sheldon, Haris Shuaib, James Teo, Joshua Au Yeung, Kawsar Noor, Mohammad Al-Agil, Richard Dobson, Xi Bai, Zeljko Kraljevic","submitted_at":"2023-10-05T19:10:18Z","abstract_excerpt":"Protecting patient privacy in healthcare records is a top priority, and redaction is a commonly used method for obscuring directly identifiable information in text. Rule-based methods have been widely used, but their precision is often low causing over-redaction of text and frequently not being adaptable enough for non-standardised or unconventional structures of personal health information. Deep learning techniques have emerged as a promising solution, but implementing them in real-world environments poses challenges due to the differences in patient record structure and language across diffe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.04468","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/2310.04468/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":"2026-07-05T06:58:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6J8KuggDK4k7GIezngwy+3AFmtOz3VpQCuIZ1FWje1W38lAqzvkgmNvX8k/vUA7/CPdeyEmCGnk8uM7nIv1uDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T11:01:54.526753Z"},"content_sha256":"b598d720c4e583a16d52e5a0d6a287e8c74d274c7a9a551d7f54291b411164f2","schema_version":"1.0","event_id":"sha256:b598d720c4e583a16d52e5a0d6a287e8c74d274c7a9a551d7f54291b411164f2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5RMKWPZVR6B6EZGQ2VCUGZV2KE/bundle.json","state_url":"https://pith.science/pith/5RMKWPZVR6B6EZGQ2VCUGZV2KE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5RMKWPZVR6B6EZGQ2VCUGZV2KE/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":"2026-07-05T11:01:54Z","links":{"resolver":"https://pith.science/pith/5RMKWPZVR6B6EZGQ2VCUGZV2KE","bundle":"https://pith.science/pith/5RMKWPZVR6B6EZGQ2VCUGZV2KE/bundle.json","state":"https://pith.science/pith/5RMKWPZVR6B6EZGQ2VCUGZV2KE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5RMKWPZVR6B6EZGQ2VCUGZV2KE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5RMKWPZVR6B6EZGQ2VCUGZV2KE","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":"71120c66f8e4ec98a5e375c9e82bbcccc6a2dc4f7cfbd19d7d211be5e4f7fabc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-05T19:10:18Z","title_canon_sha256":"419d6f550b5f67ddfe4dec04ac7fa0c223227f724e801caa57e4045e1ae2abc5"},"schema_version":"1.0","source":{"id":"2310.04468","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.04468","created_at":"2026-07-05T06:58:18Z"},{"alias_kind":"arxiv_version","alias_value":"2310.04468v1","created_at":"2026-07-05T06:58:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.04468","created_at":"2026-07-05T06:58:18Z"},{"alias_kind":"pith_short_12","alias_value":"5RMKWPZVR6B6","created_at":"2026-07-05T06:58:18Z"},{"alias_kind":"pith_short_16","alias_value":"5RMKWPZVR6B6EZGQ","created_at":"2026-07-05T06:58:18Z"},{"alias_kind":"pith_short_8","alias_value":"5RMKWPZV","created_at":"2026-07-05T06:58:18Z"}],"graph_snapshots":[{"event_id":"sha256:b598d720c4e583a16d52e5a0d6a287e8c74d274c7a9a551d7f54291b411164f2","target":"graph","created_at":"2026-07-05T06:58:18Z","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/2310.04468/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Protecting patient privacy in healthcare records is a top priority, and redaction is a commonly used method for obscuring directly identifiable information in text. Rule-based methods have been widely used, but their precision is often low causing over-redaction of text and frequently not being adaptable enough for non-standardised or unconventional structures of personal health information. Deep learning techniques have emerged as a promising solution, but implementing them in real-world environments poses challenges due to the differences in patient record structure and language across diffe","authors_text":"Anoop D. Shah, Anthony Shek, Ewart Jonathan Sheldon, Haris Shuaib, James Teo, Joshua Au Yeung, Kawsar Noor, Mohammad Al-Agil, Richard Dobson, Xi Bai, Zeljko Kraljevic","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-05T19:10:18Z","title":"Validating transformers for redaction of text from electronic health records in real-world healthcare"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.04468","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":"sha256:8a3af4c1909bce9651d864a5d84dd031fef6831d75e5d06686415d40a328a1d0","target":"record","created_at":"2026-07-05T06:58:18Z","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":"71120c66f8e4ec98a5e375c9e82bbcccc6a2dc4f7cfbd19d7d211be5e4f7fabc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-05T19:10:18Z","title_canon_sha256":"419d6f550b5f67ddfe4dec04ac7fa0c223227f724e801caa57e4045e1ae2abc5"},"schema_version":"1.0","source":{"id":"2310.04468","kind":"arxiv","version":1}},"canonical_sha256":"ec58ab3f358f83e264d0d5454366ba511e9f201b4f99f2cde6384e508428c8fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec58ab3f358f83e264d0d5454366ba511e9f201b4f99f2cde6384e508428c8fd","first_computed_at":"2026-07-05T06:58:18.792033Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:58:18.792033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4EOej3YJy5m9lJgTZPPhCDtNVQUwejPilUdPzwAGwbkUFyOPuKv5Vpal1RwHwaN+UMemn0usjN90FxKVXmFHAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:58:18.792517Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.04468","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a3af4c1909bce9651d864a5d84dd031fef6831d75e5d06686415d40a328a1d0","sha256:b598d720c4e583a16d52e5a0d6a287e8c74d274c7a9a551d7f54291b411164f2"],"state_sha256":"76b489a54f86e1461c6c3e36ae0b68a705da84c39ce7c642a67b3e857b37df7a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YWOGhiPMTYRbDxoSTek+F23XfCI44sqI2bUQEzJZ3aSkEpqnrumEQzcBMxkBiSifPxicMpRkO7uJajsUwcjMAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T11:01:54.528766Z","bundle_sha256":"2edeccef3b9eb2e61a7453296bb4e195d6093de22ae949278b1e15a3b4c635a0"}}