{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QHYKE74CTJ7H6LJEUWBFGVQN4T","short_pith_number":"pith:QHYKE74C","canonical_record":{"source":{"id":"2501.02407","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-05T00:03:18Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"0fee9ead890716f6c472ccc390bf192a037d315018c0cf6ed143cd058341df5c","abstract_canon_sha256":"238d534e68dc96ab245ca833dc0f2cd3c23d63b4b209a56ad0d4bd9e93528f02"},"schema_version":"1.0"},"canonical_sha256":"81f0a27f829a7e7f2d24a58253560de4ed2d46bef34ab4d53234d334db01db89","source":{"kind":"arxiv","id":"2501.02407","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.02407","created_at":"2026-05-21T01:05:03Z"},{"alias_kind":"arxiv_version","alias_value":"2501.02407v3","created_at":"2026-05-21T01:05:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.02407","created_at":"2026-05-21T01:05:03Z"},{"alias_kind":"pith_short_12","alias_value":"QHYKE74CTJ7H","created_at":"2026-05-21T01:05:03Z"},{"alias_kind":"pith_short_16","alias_value":"QHYKE74CTJ7H6LJE","created_at":"2026-05-21T01:05:03Z"},{"alias_kind":"pith_short_8","alias_value":"QHYKE74C","created_at":"2026-05-21T01:05:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QHYKE74CTJ7H6LJEUWBFGVQN4T","target":"record","payload":{"canonical_record":{"source":{"id":"2501.02407","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-05T00:03:18Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"0fee9ead890716f6c472ccc390bf192a037d315018c0cf6ed143cd058341df5c","abstract_canon_sha256":"238d534e68dc96ab245ca833dc0f2cd3c23d63b4b209a56ad0d4bd9e93528f02"},"schema_version":"1.0"},"canonical_sha256":"81f0a27f829a7e7f2d24a58253560de4ed2d46bef34ab4d53234d334db01db89","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:03.993844Z","signature_b64":"xPDTu/hzafLuIraFxRfgPl7h7slrd7fQLHOtioN6Xp7Mi5JYTIA/4MDLcGIbcqP6PtRTC+NK7EbXbGzk0JdSDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81f0a27f829a7e7f2d24a58253560de4ed2d46bef34ab4d53234d334db01db89","last_reissued_at":"2026-05-21T01:05:03.992950Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:03.992950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.02407","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T01:05:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sN9UPOgtn5dQ0SdzALsI9HWEXtgDyiNK2xCWAyO6E46IKWBdNpQYrQXkgR6VydGhNxOC7BYelDLjbpYX13MUDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T11:38:34.184968Z"},"content_sha256":"19a51c56df7bc52e02be391ca8e382cd864b5533857eb133294be0829bb11da3","schema_version":"1.0","event_id":"sha256:19a51c56df7bc52e02be391ca8e382cd864b5533857eb133294be0829bb11da3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QHYKE74CTJ7H6LJEUWBFGVQN4T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards the Anonymization of the Language Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Antoine Boutet, Juliette S\\'en\\'echal, Lucas Magnana","submitted_at":"2025-01-05T00:03:18Z","abstract_excerpt":"Rapid advances in Natural Language Processing (NLP) have revolutionized many fields, including healthcare. However, these advances raise significant privacy concerns, especially when pre-trained models fine-tuned and specialized on sensitive data can memorize and then expose and regurgitate personal information. This paper presents a privacy-preserving language modeling approach to address the problem of language models anonymization, and thus promote their sharing. Specifically, we propose both a Masking Language Modeling (MLM) methodology to specialize a BERT-like language model, and a Causa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02407","kind":"arxiv","version":3},"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/2501.02407/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":"2026-05-21T01:05:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vDiq1eSzHhq8dI+VeETg6XA20GDaaPu773LgM/mE1HWm9v9b6c/108wHBYe/U1FXbszuFHcsGqiZadw1NgPzAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T11:38:34.185660Z"},"content_sha256":"69880666085bf6a0c73f0b9f96b31826e2ea050c4235bd416279768cf4e3587e","schema_version":"1.0","event_id":"sha256:69880666085bf6a0c73f0b9f96b31826e2ea050c4235bd416279768cf4e3587e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QHYKE74CTJ7H6LJEUWBFGVQN4T/bundle.json","state_url":"https://pith.science/pith/QHYKE74CTJ7H6LJEUWBFGVQN4T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QHYKE74CTJ7H6LJEUWBFGVQN4T/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":"2026-05-31T11:38:34Z","links":{"resolver":"https://pith.science/pith/QHYKE74CTJ7H6LJEUWBFGVQN4T","bundle":"https://pith.science/pith/QHYKE74CTJ7H6LJEUWBFGVQN4T/bundle.json","state":"https://pith.science/pith/QHYKE74CTJ7H6LJEUWBFGVQN4T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QHYKE74CTJ7H6LJEUWBFGVQN4T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QHYKE74CTJ7H6LJEUWBFGVQN4T","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":"238d534e68dc96ab245ca833dc0f2cd3c23d63b4b209a56ad0d4bd9e93528f02","cross_cats_sorted":["cs.CR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-05T00:03:18Z","title_canon_sha256":"0fee9ead890716f6c472ccc390bf192a037d315018c0cf6ed143cd058341df5c"},"schema_version":"1.0","source":{"id":"2501.02407","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.02407","created_at":"2026-05-21T01:05:03Z"},{"alias_kind":"arxiv_version","alias_value":"2501.02407v3","created_at":"2026-05-21T01:05:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.02407","created_at":"2026-05-21T01:05:03Z"},{"alias_kind":"pith_short_12","alias_value":"QHYKE74CTJ7H","created_at":"2026-05-21T01:05:03Z"},{"alias_kind":"pith_short_16","alias_value":"QHYKE74CTJ7H6LJE","created_at":"2026-05-21T01:05:03Z"},{"alias_kind":"pith_short_8","alias_value":"QHYKE74C","created_at":"2026-05-21T01:05:03Z"}],"graph_snapshots":[{"event_id":"sha256:69880666085bf6a0c73f0b9f96b31826e2ea050c4235bd416279768cf4e3587e","target":"graph","created_at":"2026-05-21T01:05:03Z","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/2501.02407/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Rapid advances in Natural Language Processing (NLP) have revolutionized many fields, including healthcare. However, these advances raise significant privacy concerns, especially when pre-trained models fine-tuned and specialized on sensitive data can memorize and then expose and regurgitate personal information. This paper presents a privacy-preserving language modeling approach to address the problem of language models anonymization, and thus promote their sharing. Specifically, we propose both a Masking Language Modeling (MLM) methodology to specialize a BERT-like language model, and a Causa","authors_text":"Antoine Boutet, Juliette S\\'en\\'echal, Lucas Magnana","cross_cats":["cs.CR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-05T00:03:18Z","title":"Towards the Anonymization of the Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02407","kind":"arxiv","version":3},"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":"sha256:19a51c56df7bc52e02be391ca8e382cd864b5533857eb133294be0829bb11da3","target":"record","created_at":"2026-05-21T01:05:03Z","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":"238d534e68dc96ab245ca833dc0f2cd3c23d63b4b209a56ad0d4bd9e93528f02","cross_cats_sorted":["cs.CR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-05T00:03:18Z","title_canon_sha256":"0fee9ead890716f6c472ccc390bf192a037d315018c0cf6ed143cd058341df5c"},"schema_version":"1.0","source":{"id":"2501.02407","kind":"arxiv","version":3}},"canonical_sha256":"81f0a27f829a7e7f2d24a58253560de4ed2d46bef34ab4d53234d334db01db89","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81f0a27f829a7e7f2d24a58253560de4ed2d46bef34ab4d53234d334db01db89","first_computed_at":"2026-05-21T01:05:03.992950Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:05:03.992950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xPDTu/hzafLuIraFxRfgPl7h7slrd7fQLHOtioN6Xp7Mi5JYTIA/4MDLcGIbcqP6PtRTC+NK7EbXbGzk0JdSDg==","signature_status":"signed_v1","signed_at":"2026-05-21T01:05:03.993844Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.02407","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19a51c56df7bc52e02be391ca8e382cd864b5533857eb133294be0829bb11da3","sha256:69880666085bf6a0c73f0b9f96b31826e2ea050c4235bd416279768cf4e3587e"],"state_sha256":"6373765441fbf4d348bffd73c741495482a43a0d5af4a3dddf182a415d169cb7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C7cK+ZQ4qFbgOx4h9xXc7VbfL8gVciBIXek4VAAlIcoia3mB2LWDNDxj6sAjn9JiKxWsd/JjRIGNR/Nr1ZaFCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T11:38:34.189589Z","bundle_sha256":"3d99558f5338f1317bc7a49fb2533abebec29cc157f95104e38616bd480cb099"}}