{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:6NCMHOS6XDA2EH746YI75R4LOQ","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":"191ce31e97137cc4418baaa378d83a52cb283aa97c5a637628e8bb254b53e9ff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-20T18:54:39Z","title_canon_sha256":"ddbda41d40fb541730b1c78d00860bf36bcb3f31770903381c293da4984a67b5"},"schema_version":"1.0","source":{"id":"2210.11528","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.11528","created_at":"2026-07-05T05:08:54Z"},{"alias_kind":"arxiv_version","alias_value":"2210.11528v1","created_at":"2026-07-05T05:08:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.11528","created_at":"2026-07-05T05:08:54Z"},{"alias_kind":"pith_short_12","alias_value":"6NCMHOS6XDA2","created_at":"2026-07-05T05:08:54Z"},{"alias_kind":"pith_short_16","alias_value":"6NCMHOS6XDA2EH74","created_at":"2026-07-05T05:08:54Z"},{"alias_kind":"pith_short_8","alias_value":"6NCMHOS6","created_at":"2026-07-05T05:08:54Z"}],"graph_snapshots":[{"event_id":"sha256:740b5c5d1c6a69a0692aedc9fb64ace7c44b75deb773c7092e60f0b5147960e8","target":"graph","created_at":"2026-07-05T05:08:54Z","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/2210.11528/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deidentification seeks to anonymize textual data prior to distribution. Automatic deidentification primarily uses supervised named entity recognition from human-labeled data points. We propose an unsupervised deidentification method that masks words that leak personally-identifying information. The approach utilizes a specially trained reidentification model to identify individuals from redacted personal documents. Motivated by K-anonymity based privacy, we generate redactions that ensure a minimum reidentification rank for the correct profile of the document. To evaluate this approach, we con","authors_text":"Alexander M. Rush, John X. Morris, Justin T. Chiu, Ramin Zabih","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-20T18:54:39Z","title":"Unsupervised Text Deidentification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11528","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":"sha256:74b5a2351d4f81c0cf37c0be6a3ee49d429048333d79722185c3d9970158fe5e","target":"record","created_at":"2026-07-05T05:08:54Z","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":"191ce31e97137cc4418baaa378d83a52cb283aa97c5a637628e8bb254b53e9ff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-20T18:54:39Z","title_canon_sha256":"ddbda41d40fb541730b1c78d00860bf36bcb3f31770903381c293da4984a67b5"},"schema_version":"1.0","source":{"id":"2210.11528","kind":"arxiv","version":1}},"canonical_sha256":"f344c3ba5eb8c1a21ffcf611fec78b741708e7dc5aa79e6b8902da61c91e7a17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f344c3ba5eb8c1a21ffcf611fec78b741708e7dc5aa79e6b8902da61c91e7a17","first_computed_at":"2026-07-05T05:08:54.543555Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:08:54.543555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q8t8gOP1yz/Ap5DDWSUmuvgT3ta/av0EetxSCyVm8vZ5jjbrPHCaCyXALpK2x+bh+A9xSDvySqcc53pNPoSZCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:08:54.543966Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.11528","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:74b5a2351d4f81c0cf37c0be6a3ee49d429048333d79722185c3d9970158fe5e","sha256:740b5c5d1c6a69a0692aedc9fb64ace7c44b75deb773c7092e60f0b5147960e8"],"state_sha256":"3ee6303e7462f205b04a72fdb8a63a6d2261a899334e2dc03529af46ec20c9b7"}