{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6NCMHOS6XDA2EH746YI75R4LOQ","short_pith_number":"pith:6NCMHOS6","schema_version":"1.0","canonical_sha256":"f344c3ba5eb8c1a21ffcf611fec78b741708e7dc5aa79e6b8902da61c91e7a17","source":{"kind":"arxiv","id":"2210.11528","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Text Deidentification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander M. Rush, John X. Morris, Justin T. Chiu, Ramin Zabih","submitted_at":"2022-10-20T18:54:39Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2210.11528","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-20T18:54:39Z","cross_cats_sorted":[],"title_canon_sha256":"ddbda41d40fb541730b1c78d00860bf36bcb3f31770903381c293da4984a67b5","abstract_canon_sha256":"191ce31e97137cc4418baaa378d83a52cb283aa97c5a637628e8bb254b53e9ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:54.543966Z","signature_b64":"Q8t8gOP1yz/Ap5DDWSUmuvgT3ta/av0EetxSCyVm8vZ5jjbrPHCaCyXALpK2x+bh+A9xSDvySqcc53pNPoSZCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f344c3ba5eb8c1a21ffcf611fec78b741708e7dc5aa79e6b8902da61c91e7a17","last_reissued_at":"2026-07-05T05:08:54.543555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:54.543555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Text Deidentification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander M. Rush, John X. Morris, Justin T. Chiu, Ramin Zabih","submitted_at":"2022-10-20T18:54:39Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11528","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/2210.11528/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2210.11528","created_at":"2026-07-05T05:08:54.543611+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.11528v1","created_at":"2026-07-05T05:08:54.543611+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.11528","created_at":"2026-07-05T05:08:54.543611+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NCMHOS6XDA2","created_at":"2026-07-05T05:08:54.543611+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NCMHOS6XDA2EH74","created_at":"2026-07-05T05:08:54.543611+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NCMHOS6","created_at":"2026-07-05T05:08:54.543611+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6NCMHOS6XDA2EH746YI75R4LOQ","json":"https://pith.science/pith/6NCMHOS6XDA2EH746YI75R4LOQ.json","graph_json":"https://pith.science/api/pith-number/6NCMHOS6XDA2EH746YI75R4LOQ/graph.json","events_json":"https://pith.science/api/pith-number/6NCMHOS6XDA2EH746YI75R4LOQ/events.json","paper":"https://pith.science/paper/6NCMHOS6"},"agent_actions":{"view_html":"https://pith.science/pith/6NCMHOS6XDA2EH746YI75R4LOQ","download_json":"https://pith.science/pith/6NCMHOS6XDA2EH746YI75R4LOQ.json","view_paper":"https://pith.science/paper/6NCMHOS6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.11528&json=true","fetch_graph":"https://pith.science/api/pith-number/6NCMHOS6XDA2EH746YI75R4LOQ/graph.json","fetch_events":"https://pith.science/api/pith-number/6NCMHOS6XDA2EH746YI75R4LOQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NCMHOS6XDA2EH746YI75R4LOQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NCMHOS6XDA2EH746YI75R4LOQ/action/storage_attestation","attest_author":"https://pith.science/pith/6NCMHOS6XDA2EH746YI75R4LOQ/action/author_attestation","sign_citation":"https://pith.science/pith/6NCMHOS6XDA2EH746YI75R4LOQ/action/citation_signature","submit_replication":"https://pith.science/pith/6NCMHOS6XDA2EH746YI75R4LOQ/action/replication_record"}},"created_at":"2026-07-05T05:08:54.543611+00:00","updated_at":"2026-07-05T05:08:54.543611+00:00"}