{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3UGM53IIOCAOMBSSKEK63RQOKQ","short_pith_number":"pith:3UGM53II","canonical_record":{"source":{"id":"2505.21128","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.AP","submitted_at":"2025-05-27T12:45:45Z","cross_cats_sorted":[],"title_canon_sha256":"89e10afd83b49f9d91e3c74f3a73c859282adf07cda4d95db7f50f937f46102d","abstract_canon_sha256":"2190bbf5fda340c82a97ed61edccd0e83dfbe6a3c79c7b6dc1b67ffe373e4866"},"schema_version":"1.0"},"canonical_sha256":"dd0cceed087080e606525115edc60e5428966f3de48a6d454a0d8503602e638e","source":{"kind":"arxiv","id":"2505.21128","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21128","created_at":"2026-07-05T11:10:24Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21128v1","created_at":"2026-07-05T11:10:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21128","created_at":"2026-07-05T11:10:24Z"},{"alias_kind":"pith_short_12","alias_value":"3UGM53IIOCAO","created_at":"2026-07-05T11:10:24Z"},{"alias_kind":"pith_short_16","alias_value":"3UGM53IIOCAOMBSS","created_at":"2026-07-05T11:10:24Z"},{"alias_kind":"pith_short_8","alias_value":"3UGM53II","created_at":"2026-07-05T11:10:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3UGM53IIOCAOMBSSKEK63RQOKQ","target":"record","payload":{"canonical_record":{"source":{"id":"2505.21128","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.AP","submitted_at":"2025-05-27T12:45:45Z","cross_cats_sorted":[],"title_canon_sha256":"89e10afd83b49f9d91e3c74f3a73c859282adf07cda4d95db7f50f937f46102d","abstract_canon_sha256":"2190bbf5fda340c82a97ed61edccd0e83dfbe6a3c79c7b6dc1b67ffe373e4866"},"schema_version":"1.0"},"canonical_sha256":"dd0cceed087080e606525115edc60e5428966f3de48a6d454a0d8503602e638e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:24.090547Z","signature_b64":"FuquHvOoGdRsnUPywr/xmq2TiSN2HoxG/gO5wr1mnktNuwj1cYlZMeHG/xdKD9luB8Y68etbHmEo9FWWO+FRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd0cceed087080e606525115edc60e5428966f3de48a6d454a0d8503602e638e","last_reissued_at":"2026-07-05T11:10:24.090062Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:24.090062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.21128","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":"2026-07-05T11:10:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pNDZSwWjSdgejgfNw1H5EACQIRDWII92jBvRi+CuJQpamEOaHBJ2kt33E+lXBX8Wru5dWlSpvd5NOx79jiI+Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:53:44.957212Z"},"content_sha256":"8642a29f4fac70339fc84c840815368b3faf9a50bfcc44688e2e4750bb95a8c3","schema_version":"1.0","event_id":"sha256:8642a29f4fac70339fc84c840815368b3faf9a50bfcc44688e2e4750bb95a8c3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3UGM53IIOCAOMBSSKEK63RQOKQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Named Entity Swapping for Metadata Anonymization in a Text Corpus","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"stat.AP","authors_text":"Jan Greve, Lukas Sablica","submitted_at":"2025-05-27T12:45:45Z","abstract_excerpt":"This work introduces an anonymization scheme for a corpus of texts to safeguard metadata from disclosure. It specifically aims to prevent large language models from identifying metadata associated with texts, thereby avoiding their influence on query responses. The core mechanism is called named entity swapping, a technique inspired by data swapping in statistical disclosure control. Our method randomly selects pairs of semantically similar substrings from different texts based on the similarity of their embedding vectors and interchanges some named entities between them. This prevents certain"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21128","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/2505.21128/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":"2026-07-05T11:10:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JW7PQPLrUDmWCHmlznxjGErbSsIXRSF2kJ6/G6KsCoMUDNrg0D7i5unirZNcdbaoAFQHn8oKxjskq4zGiGG8Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:53:44.957699Z"},"content_sha256":"f909bc616d840810f4db231fa386f9ed626be6d88c72ba9f94e698b38ab7f0ce","schema_version":"1.0","event_id":"sha256:f909bc616d840810f4db231fa386f9ed626be6d88c72ba9f94e698b38ab7f0ce"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3UGM53IIOCAOMBSSKEK63RQOKQ/bundle.json","state_url":"https://pith.science/pith/3UGM53IIOCAOMBSSKEK63RQOKQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3UGM53IIOCAOMBSSKEK63RQOKQ/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":"2026-08-07T23:53:44Z","links":{"resolver":"https://pith.science/pith/3UGM53IIOCAOMBSSKEK63RQOKQ","bundle":"https://pith.science/pith/3UGM53IIOCAOMBSSKEK63RQOKQ/bundle.json","state":"https://pith.science/pith/3UGM53IIOCAOMBSSKEK63RQOKQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3UGM53IIOCAOMBSSKEK63RQOKQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3UGM53IIOCAOMBSSKEK63RQOKQ","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":"2190bbf5fda340c82a97ed61edccd0e83dfbe6a3c79c7b6dc1b67ffe373e4866","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.AP","submitted_at":"2025-05-27T12:45:45Z","title_canon_sha256":"89e10afd83b49f9d91e3c74f3a73c859282adf07cda4d95db7f50f937f46102d"},"schema_version":"1.0","source":{"id":"2505.21128","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21128","created_at":"2026-07-05T11:10:24Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21128v1","created_at":"2026-07-05T11:10:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21128","created_at":"2026-07-05T11:10:24Z"},{"alias_kind":"pith_short_12","alias_value":"3UGM53IIOCAO","created_at":"2026-07-05T11:10:24Z"},{"alias_kind":"pith_short_16","alias_value":"3UGM53IIOCAOMBSS","created_at":"2026-07-05T11:10:24Z"},{"alias_kind":"pith_short_8","alias_value":"3UGM53II","created_at":"2026-07-05T11:10:24Z"}],"graph_snapshots":[{"event_id":"sha256:f909bc616d840810f4db231fa386f9ed626be6d88c72ba9f94e698b38ab7f0ce","target":"graph","created_at":"2026-07-05T11:10:24Z","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/2505.21128/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work introduces an anonymization scheme for a corpus of texts to safeguard metadata from disclosure. It specifically aims to prevent large language models from identifying metadata associated with texts, thereby avoiding their influence on query responses. The core mechanism is called named entity swapping, a technique inspired by data swapping in statistical disclosure control. Our method randomly selects pairs of semantically similar substrings from different texts based on the similarity of their embedding vectors and interchanges some named entities between them. This prevents certain","authors_text":"Jan Greve, Lukas Sablica","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.AP","submitted_at":"2025-05-27T12:45:45Z","title":"Named Entity Swapping for Metadata Anonymization in a Text Corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21128","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":"sha256:8642a29f4fac70339fc84c840815368b3faf9a50bfcc44688e2e4750bb95a8c3","target":"record","created_at":"2026-07-05T11:10:24Z","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":"2190bbf5fda340c82a97ed61edccd0e83dfbe6a3c79c7b6dc1b67ffe373e4866","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.AP","submitted_at":"2025-05-27T12:45:45Z","title_canon_sha256":"89e10afd83b49f9d91e3c74f3a73c859282adf07cda4d95db7f50f937f46102d"},"schema_version":"1.0","source":{"id":"2505.21128","kind":"arxiv","version":1}},"canonical_sha256":"dd0cceed087080e606525115edc60e5428966f3de48a6d454a0d8503602e638e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd0cceed087080e606525115edc60e5428966f3de48a6d454a0d8503602e638e","first_computed_at":"2026-07-05T11:10:24.090062Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:24.090062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FuquHvOoGdRsnUPywr/xmq2TiSN2HoxG/gO5wr1mnktNuwj1cYlZMeHG/xdKD9luB8Y68etbHmEo9FWWO+FRCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:24.090547Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.21128","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8642a29f4fac70339fc84c840815368b3faf9a50bfcc44688e2e4750bb95a8c3","sha256:f909bc616d840810f4db231fa386f9ed626be6d88c72ba9f94e698b38ab7f0ce"],"state_sha256":"7b5b839fc1ba861da7e0dc1f535b4c1319e72982dff95fd1456bdeca846d70cb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NTCX/4erjb0UinlpgzxPCpF/xBHaUJMipxDp9nK7whXNyL/MAdEPLoj2U6d3IAxx1HrNNnY+2X8ishrNvRAJCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:53:44.961976Z","bundle_sha256":"df4999e88ea7dc1e7a9f95f35d528264195a28900a3ca805d743e0280f79fccb"}}