{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:OS5KYFIRL253T7ZKBBVGSRNNZV","short_pith_number":"pith:OS5KYFIR","canonical_record":{"source":{"id":"2105.09198","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-19T15:17:44Z","cross_cats_sorted":[],"title_canon_sha256":"470e588f0be6fe8a37dbd228ce824cc465b407cd94b9e723d575144b283d9ad3","abstract_canon_sha256":"22295ab8be0c882e491f42da4be21c8e69d10636de616bfce3aae6c25b72a8b9"},"schema_version":"1.0"},"canonical_sha256":"74baac15115ebbb9ff2a086a6945adcd7c03f01184dee348fd0371af0bd3b883","source":{"kind":"arxiv","id":"2105.09198","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.09198","created_at":"2026-07-05T02:41:38Z"},{"alias_kind":"arxiv_version","alias_value":"2105.09198v1","created_at":"2026-07-05T02:41:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.09198","created_at":"2026-07-05T02:41:38Z"},{"alias_kind":"pith_short_12","alias_value":"OS5KYFIRL253","created_at":"2026-07-05T02:41:38Z"},{"alias_kind":"pith_short_16","alias_value":"OS5KYFIRL253T7ZK","created_at":"2026-07-05T02:41:38Z"},{"alias_kind":"pith_short_8","alias_value":"OS5KYFIR","created_at":"2026-07-05T02:41:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:OS5KYFIRL253T7ZKBBVGSRNNZV","target":"record","payload":{"canonical_record":{"source":{"id":"2105.09198","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-19T15:17:44Z","cross_cats_sorted":[],"title_canon_sha256":"470e588f0be6fe8a37dbd228ce824cc465b407cd94b9e723d575144b283d9ad3","abstract_canon_sha256":"22295ab8be0c882e491f42da4be21c8e69d10636de616bfce3aae6c25b72a8b9"},"schema_version":"1.0"},"canonical_sha256":"74baac15115ebbb9ff2a086a6945adcd7c03f01184dee348fd0371af0bd3b883","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:41:38.563293Z","signature_b64":"YGdyoS3kKK0PCgzQsQFGHVz3HIOwaUd+4kam1E7hJa+RiLBrjBZyDyfKCC/8VoNsmnVfyzWNfTWJ44W8OtVHBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74baac15115ebbb9ff2a086a6945adcd7c03f01184dee348fd0371af0bd3b883","last_reissued_at":"2026-07-05T02:41:38.562822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:41:38.562822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.09198","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":"2026-07-05T02:41:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cCLQyRLdIPI7ylIfdhvi61XH1CzhND+cMyYqahXq7VI5ZOUVAZH0uFTVr8VU4XteCwmMxxg6h9RId/NvaRvhBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:57:26.169377Z"},"content_sha256":"64bd4ec238e123bef13e45c2cd70c6016a1a62b78c408925a7cf2f9e6cd010d9","schema_version":"1.0","event_id":"sha256:64bd4ec238e123bef13e45c2cd70c6016a1a62b78c408925a7cf2f9e6cd010d9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:OS5KYFIRL253T7ZKBBVGSRNNZV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Privacy-Preserving Approach to Extraction of Personal Information through Automatic Annotation and Federated Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Isar Nejadgholi, Miodrag Bolic, Rajitha Hathurusinghe","submitted_at":"2021-05-19T15:17:44Z","abstract_excerpt":"We curated WikiPII, an automatically labeled dataset composed of Wikipedia biography pages, annotated for personal information extraction. Although automatic annotation can lead to a high degree of label noise, it is an inexpensive process and can generate large volumes of annotated documents. We trained a BERT-based NER model with WikiPII and showed that with an adequately large training dataset, the model can significantly decrease the cost of manual information extraction, despite the high level of label noise. In a similar approach, organizations can leverage text mining techniques to crea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.09198","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/2105.09198/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":"2026-07-05T02:41:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1ng6P71YHaD6f/0Wj4dERPzu8o3mL66G2CetdEpvvYumegumxldedCFucFwJdHgVSsnhm6vuWBsWmA4I5pe5Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:57:26.169869Z"},"content_sha256":"a7019a5a4345f6c63d35b12acefd3e50b2fe03af582fe060855ec2e66b51bcbf","schema_version":"1.0","event_id":"sha256:a7019a5a4345f6c63d35b12acefd3e50b2fe03af582fe060855ec2e66b51bcbf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OS5KYFIRL253T7ZKBBVGSRNNZV/bundle.json","state_url":"https://pith.science/pith/OS5KYFIRL253T7ZKBBVGSRNNZV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OS5KYFIRL253T7ZKBBVGSRNNZV/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":"2026-08-08T23:57:26Z","links":{"resolver":"https://pith.science/pith/OS5KYFIRL253T7ZKBBVGSRNNZV","bundle":"https://pith.science/pith/OS5KYFIRL253T7ZKBBVGSRNNZV/bundle.json","state":"https://pith.science/pith/OS5KYFIRL253T7ZKBBVGSRNNZV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OS5KYFIRL253T7ZKBBVGSRNNZV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:OS5KYFIRL253T7ZKBBVGSRNNZV","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":"22295ab8be0c882e491f42da4be21c8e69d10636de616bfce3aae6c25b72a8b9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-19T15:17:44Z","title_canon_sha256":"470e588f0be6fe8a37dbd228ce824cc465b407cd94b9e723d575144b283d9ad3"},"schema_version":"1.0","source":{"id":"2105.09198","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.09198","created_at":"2026-07-05T02:41:38Z"},{"alias_kind":"arxiv_version","alias_value":"2105.09198v1","created_at":"2026-07-05T02:41:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.09198","created_at":"2026-07-05T02:41:38Z"},{"alias_kind":"pith_short_12","alias_value":"OS5KYFIRL253","created_at":"2026-07-05T02:41:38Z"},{"alias_kind":"pith_short_16","alias_value":"OS5KYFIRL253T7ZK","created_at":"2026-07-05T02:41:38Z"},{"alias_kind":"pith_short_8","alias_value":"OS5KYFIR","created_at":"2026-07-05T02:41:38Z"}],"graph_snapshots":[{"event_id":"sha256:a7019a5a4345f6c63d35b12acefd3e50b2fe03af582fe060855ec2e66b51bcbf","target":"graph","created_at":"2026-07-05T02:41:38Z","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/2105.09198/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We curated WikiPII, an automatically labeled dataset composed of Wikipedia biography pages, annotated for personal information extraction. Although automatic annotation can lead to a high degree of label noise, it is an inexpensive process and can generate large volumes of annotated documents. We trained a BERT-based NER model with WikiPII and showed that with an adequately large training dataset, the model can significantly decrease the cost of manual information extraction, despite the high level of label noise. In a similar approach, organizations can leverage text mining techniques to crea","authors_text":"Isar Nejadgholi, Miodrag Bolic, Rajitha Hathurusinghe","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-19T15:17:44Z","title":"A Privacy-Preserving Approach to Extraction of Personal Information through Automatic Annotation and Federated Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.09198","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":"sha256:64bd4ec238e123bef13e45c2cd70c6016a1a62b78c408925a7cf2f9e6cd010d9","target":"record","created_at":"2026-07-05T02:41:38Z","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":"22295ab8be0c882e491f42da4be21c8e69d10636de616bfce3aae6c25b72a8b9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-19T15:17:44Z","title_canon_sha256":"470e588f0be6fe8a37dbd228ce824cc465b407cd94b9e723d575144b283d9ad3"},"schema_version":"1.0","source":{"id":"2105.09198","kind":"arxiv","version":1}},"canonical_sha256":"74baac15115ebbb9ff2a086a6945adcd7c03f01184dee348fd0371af0bd3b883","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74baac15115ebbb9ff2a086a6945adcd7c03f01184dee348fd0371af0bd3b883","first_computed_at":"2026-07-05T02:41:38.562822Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:41:38.562822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YGdyoS3kKK0PCgzQsQFGHVz3HIOwaUd+4kam1E7hJa+RiLBrjBZyDyfKCC/8VoNsmnVfyzWNfTWJ44W8OtVHBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:41:38.563293Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.09198","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64bd4ec238e123bef13e45c2cd70c6016a1a62b78c408925a7cf2f9e6cd010d9","sha256:a7019a5a4345f6c63d35b12acefd3e50b2fe03af582fe060855ec2e66b51bcbf"],"state_sha256":"595c88580ead6931169c4076f8a89f08007b62c2bb07b36ee4c16f83e18da44a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YjbQkZwlHgOOFTg7l01Xg2hJaUI94zXI8pZqky34eATrhao80Y0Aike181zGiExeE/aHVYZskaUEM9nX3iAoAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T23:57:26.173583Z","bundle_sha256":"9ce759894bc2e0d824d5389f7ad9a042ed4645b75b8650f2b7590e8506e99442"}}