{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FKPAB7WBTRQH7AYLKI6HCIYIWR","short_pith_number":"pith:FKPAB7WB","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"},"canonical_sha256":"2a9e00fec19c607f830b523c712308b45cf53787c735078641c45f5426fcd904","source":{"kind":"arxiv","id":"2310.14312","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.14312","created_at":"2026-07-05T07:03:42Z"},{"alias_kind":"arxiv_version","alias_value":"2310.14312v1","created_at":"2026-07-05T07:03:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14312","created_at":"2026-07-05T07:03:42Z"},{"alias_kind":"pith_short_12","alias_value":"FKPAB7WBTRQH","created_at":"2026-07-05T07:03:42Z"},{"alias_kind":"pith_short_16","alias_value":"FKPAB7WBTRQH7AYL","created_at":"2026-07-05T07:03:42Z"},{"alias_kind":"pith_short_8","alias_value":"FKPAB7WB","created_at":"2026-07-05T07:03:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FKPAB7WBTRQH7AYLKI6HCIYIWR","target":"record","payload":{"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"},"canonical_sha256":"2a9e00fec19c607f830b523c712308b45cf53787c735078641c45f5426fcd904","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"},"source_kind":"arxiv","source_id":"2310.14312","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":"2026-07-05T07:03:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y0Hyomwv/nurCm3Ux1yhBZlDeJOPuG7DqXJEQCIlpnisVOSQjYsqTwW5ud8bp0PfdWY0GK5YtmfWMC+cSnV5CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T13:49:40.196219Z"},"content_sha256":"3d3f0b3521e001278d7d11f6456e301de8aa9d294f7d409d20eb65aee148f4a8","schema_version":"1.0","event_id":"sha256:3d3f0b3521e001278d7d11f6456e301de8aa9d294f7d409d20eb65aee148f4a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FKPAB7WBTRQH7AYLKI6HCIYIWR","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:03:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GuQGcYfECOzGwZnJUi7VE4VF0GV7I/Afv3whSzwMWqkNawSLstpy/sfOkQXURDrN2PBd/mK9eY8sv1Fl4dGEDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T13:49:40.197105Z"},"content_sha256":"fd0e0609becd43c638eeea7a5bc35ffbbfa1b9d63e9316623e73a6a6fd2dfea6","schema_version":"1.0","event_id":"sha256:fd0e0609becd43c638eeea7a5bc35ffbbfa1b9d63e9316623e73a6a6fd2dfea6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FKPAB7WBTRQH7AYLKI6HCIYIWR/bundle.json","state_url":"https://pith.science/pith/FKPAB7WBTRQH7AYLKI6HCIYIWR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FKPAB7WBTRQH7AYLKI6HCIYIWR/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":"2026-08-13T13:49:40Z","links":{"resolver":"https://pith.science/pith/FKPAB7WBTRQH7AYLKI6HCIYIWR","bundle":"https://pith.science/pith/FKPAB7WBTRQH7AYLKI6HCIYIWR/bundle.json","state":"https://pith.science/pith/FKPAB7WBTRQH7AYLKI6HCIYIWR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FKPAB7WBTRQH7AYLKI6HCIYIWR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FKPAB7WBTRQH7AYLKI6HCIYIWR","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":"09e644ce44183c13058e8ad5b5bb5964b7f1d17aa5aebfb9761abd263b65ab66","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-22T14:17:27Z","title_canon_sha256":"98f09d2bad988a5b7040a6e0fc627d52be48a584b8e8887f90e316dac63fa624"},"schema_version":"1.0","source":{"id":"2310.14312","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.14312","created_at":"2026-07-05T07:03:42Z"},{"alias_kind":"arxiv_version","alias_value":"2310.14312v1","created_at":"2026-07-05T07:03:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14312","created_at":"2026-07-05T07:03:42Z"},{"alias_kind":"pith_short_12","alias_value":"FKPAB7WBTRQH","created_at":"2026-07-05T07:03:42Z"},{"alias_kind":"pith_short_16","alias_value":"FKPAB7WBTRQH7AYL","created_at":"2026-07-05T07:03:42Z"},{"alias_kind":"pith_short_8","alias_value":"FKPAB7WB","created_at":"2026-07-05T07:03:42Z"}],"graph_snapshots":[{"event_id":"sha256:fd0e0609becd43c638eeea7a5bc35ffbbfa1b9d63e9316623e73a6a6fd2dfea6","target":"graph","created_at":"2026-07-05T07:03:42Z","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/2310.14312/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Anthi Papadopoulou, Ildik\\'o Pil\\'an, Lilja {\\O}vrelid, Mark Anderson, Pierre Lison","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-22T14:17:27Z","title":"Neural Text Sanitization with Privacy Risk Indicators: An Empirical Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14312","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":"sha256:3d3f0b3521e001278d7d11f6456e301de8aa9d294f7d409d20eb65aee148f4a8","target":"record","created_at":"2026-07-05T07:03:42Z","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":"09e644ce44183c13058e8ad5b5bb5964b7f1d17aa5aebfb9761abd263b65ab66","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-22T14:17:27Z","title_canon_sha256":"98f09d2bad988a5b7040a6e0fc627d52be48a584b8e8887f90e316dac63fa624"},"schema_version":"1.0","source":{"id":"2310.14312","kind":"arxiv","version":1}},"canonical_sha256":"2a9e00fec19c607f830b523c712308b45cf53787c735078641c45f5426fcd904","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a9e00fec19c607f830b523c712308b45cf53787c735078641c45f5426fcd904","first_computed_at":"2026-07-05T07:03:42.627033Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:03:42.627033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LQa1FVwiZ27GURAim6SbX99YotcfDPASIZCAdUHQd1VvTt+0FeGqWN2np5ixm5nPewLHb1VXe4Ae2qYApgA2DA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:03:42.627526Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.14312","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d3f0b3521e001278d7d11f6456e301de8aa9d294f7d409d20eb65aee148f4a8","sha256:fd0e0609becd43c638eeea7a5bc35ffbbfa1b9d63e9316623e73a6a6fd2dfea6"],"state_sha256":"27969892461f877553ef89fb18ee280b668fe2d5bd6ea9e48619e59df781175f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ThZOBF0EBfepPMwtW71bTmXeYmEOuJ5sH/P+2X12ai4ToX6TY8qOHZD74KS0+zotGj64czGMYXKtbGUZahbUBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T13:49:40.219862Z","bundle_sha256":"a12804ef6b35c48842670d63eb0f9e10b0f97aaac7d50415e7ca2fc893401488"}}