{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FKPAB7WBTRQH7AYLKI6HCIYIWR","short_pith_number":"pith:FKPAB7WB","schema_version":"1.0","canonical_sha256":"2a9e00fec19c607f830b523c712308b45cf53787c735078641c45f5426fcd904","source":{"kind":"arxiv","id":"2310.14312","version":1},"attestation_state":"computed","paper":{"title":"Neural Text Sanitization with Privacy Risk Indicators: An Empirical Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anthi Papadopoulou, Ildik\\'o Pil\\'an, Lilja {\\O}vrelid, Mark Anderson, Pierre Lison","submitted_at":"2023-10-22T14:17:27Z","abstract_excerpt":"Text sanitization is the task of redacting a document to mask all occurrences of (direct or indirect) personal identifiers, with the goal of concealing the identity of the individual(s) referred in it. In this paper, we consider a two-step approach to text sanitization and provide a detailed analysis of its empirical performance on two recently published datasets: the Text Anonymization Benchmark (Pil\\'an et al., 2022) and a collection of Wikipedia biographies (Papadopoulou et al., 2022). The text sanitization process starts with a privacy-oriented entity recognizer that seeks to determine the"},"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":"2310.14312","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-22T14:17:27Z","cross_cats_sorted":[],"title_canon_sha256":"98f09d2bad988a5b7040a6e0fc627d52be48a584b8e8887f90e316dac63fa624","abstract_canon_sha256":"09e644ce44183c13058e8ad5b5bb5964b7f1d17aa5aebfb9761abd263b65ab66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:42.627526Z","signature_b64":"LQa1FVwiZ27GURAim6SbX99YotcfDPASIZCAdUHQd1VvTt+0FeGqWN2np5ixm5nPewLHb1VXe4Ae2qYApgA2DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a9e00fec19c607f830b523c712308b45cf53787c735078641c45f5426fcd904","last_reissued_at":"2026-07-05T07:03:42.627033Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:42.627033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Text Sanitization with Privacy Risk Indicators: An Empirical Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anthi Papadopoulou, Ildik\\'o Pil\\'an, Lilja {\\O}vrelid, Mark Anderson, Pierre Lison","submitted_at":"2023-10-22T14:17:27Z","abstract_excerpt":"Text sanitization is the task of redacting a document to mask all occurrences of (direct or indirect) personal identifiers, with the goal of concealing the identity of the individual(s) referred in it. In this paper, we consider a two-step approach to text sanitization and provide a detailed analysis of its empirical performance on two recently published datasets: the Text Anonymization Benchmark (Pil\\'an et al., 2022) and a collection of Wikipedia biographies (Papadopoulou et al., 2022). The text sanitization process starts with a privacy-oriented entity recognizer that seeks to determine the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14312","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/2310.14312/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":"2310.14312","created_at":"2026-07-05T07:03:42.627094+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.14312v1","created_at":"2026-07-05T07:03:42.627094+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14312","created_at":"2026-07-05T07:03:42.627094+00:00"},{"alias_kind":"pith_short_12","alias_value":"FKPAB7WBTRQH","created_at":"2026-07-05T07:03:42.627094+00:00"},{"alias_kind":"pith_short_16","alias_value":"FKPAB7WBTRQH7AYL","created_at":"2026-07-05T07:03:42.627094+00:00"},{"alias_kind":"pith_short_8","alias_value":"FKPAB7WB","created_at":"2026-07-05T07:03:42.627094+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.10020","citing_title":"FindMyText: Robust, Scalable Detection of Text Containment in Large Web-Crawled Corpora","ref_index":97,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FKPAB7WBTRQH7AYLKI6HCIYIWR","json":"https://pith.science/pith/FKPAB7WBTRQH7AYLKI6HCIYIWR.json","graph_json":"https://pith.science/api/pith-number/FKPAB7WBTRQH7AYLKI6HCIYIWR/graph.json","events_json":"https://pith.science/api/pith-number/FKPAB7WBTRQH7AYLKI6HCIYIWR/events.json","paper":"https://pith.science/paper/FKPAB7WB"},"agent_actions":{"view_html":"https://pith.science/pith/FKPAB7WBTRQH7AYLKI6HCIYIWR","download_json":"https://pith.science/pith/FKPAB7WBTRQH7AYLKI6HCIYIWR.json","view_paper":"https://pith.science/paper/FKPAB7WB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.14312&json=true","fetch_graph":"https://pith.science/api/pith-number/FKPAB7WBTRQH7AYLKI6HCIYIWR/graph.json","fetch_events":"https://pith.science/api/pith-number/FKPAB7WBTRQH7AYLKI6HCIYIWR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FKPAB7WBTRQH7AYLKI6HCIYIWR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FKPAB7WBTRQH7AYLKI6HCIYIWR/action/storage_attestation","attest_author":"https://pith.science/pith/FKPAB7WBTRQH7AYLKI6HCIYIWR/action/author_attestation","sign_citation":"https://pith.science/pith/FKPAB7WBTRQH7AYLKI6HCIYIWR/action/citation_signature","submit_replication":"https://pith.science/pith/FKPAB7WBTRQH7AYLKI6HCIYIWR/action/replication_record"}},"created_at":"2026-07-05T07:03:42.627094+00:00","updated_at":"2026-07-05T07:03:42.627094+00:00"}