{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XJ6UFIEBCGOONCYZVMFQL3SYGX","short_pith_number":"pith:XJ6UFIEB","schema_version":"1.0","canonical_sha256":"ba7d42a081119ce68b19ab0b05ee5835d67234861808256c22b75424990866a8","source":{"kind":"arxiv","id":"2204.09391","version":1},"attestation_state":"computed","paper":{"title":"You Are What You Write: Preserving Privacy in the Era of Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dimitra Gkatzia, Richard Plant, Valerio Giuffrida","submitted_at":"2022-04-20T11:12:53Z","abstract_excerpt":"Large scale adoption of large language models has introduced a new era of convenient knowledge transfer for a slew of natural language processing tasks. However, these models also run the risk of undermining user trust by exposing unwanted information about the data subjects, which may be extracted by a malicious party, e.g. through adversarial attacks. We present an empirical investigation into the extent of the personal information encoded into pre-trained representations by a range of popular models, and we show a positive correlation between the complexity of a model, the amount of data us"},"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":"2204.09391","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-20T11:12:53Z","cross_cats_sorted":[],"title_canon_sha256":"d6b3b22968666dd7b7d32b81037c9345f1239570c08c83b71e9acf499f0f9c8b","abstract_canon_sha256":"6420ab8058d83641a87f352e77698f8a691ddc79a5223cf50466e113e67ed455"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:16:24.072821Z","signature_b64":"1dKPvTDCwiuwrGLO6EVhMVBjN8Ph23PKO79mg9E20FcdsM91vRfeXz2/YHwXEsOdJSqU6vKowYEJ6OLa783gAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba7d42a081119ce68b19ab0b05ee5835d67234861808256c22b75424990866a8","last_reissued_at":"2026-07-05T04:16:24.072115Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:16:24.072115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"You Are What You Write: Preserving Privacy in the Era of Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dimitra Gkatzia, Richard Plant, Valerio Giuffrida","submitted_at":"2022-04-20T11:12:53Z","abstract_excerpt":"Large scale adoption of large language models has introduced a new era of convenient knowledge transfer for a slew of natural language processing tasks. However, these models also run the risk of undermining user trust by exposing unwanted information about the data subjects, which may be extracted by a malicious party, e.g. through adversarial attacks. We present an empirical investigation into the extent of the personal information encoded into pre-trained representations by a range of popular models, and we show a positive correlation between the complexity of a model, the amount of data us"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.09391","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/2204.09391/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":"2204.09391","created_at":"2026-07-05T04:16:24.072357+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.09391v1","created_at":"2026-07-05T04:16:24.072357+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.09391","created_at":"2026-07-05T04:16:24.072357+00:00"},{"alias_kind":"pith_short_12","alias_value":"XJ6UFIEBCGOO","created_at":"2026-07-05T04:16:24.072357+00:00"},{"alias_kind":"pith_short_16","alias_value":"XJ6UFIEBCGOONCYZ","created_at":"2026-07-05T04:16:24.072357+00:00"},{"alias_kind":"pith_short_8","alias_value":"XJ6UFIEB","created_at":"2026-07-05T04:16:24.072357+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.17177","citing_title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","ref_index":133,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XJ6UFIEBCGOONCYZVMFQL3SYGX","json":"https://pith.science/pith/XJ6UFIEBCGOONCYZVMFQL3SYGX.json","graph_json":"https://pith.science/api/pith-number/XJ6UFIEBCGOONCYZVMFQL3SYGX/graph.json","events_json":"https://pith.science/api/pith-number/XJ6UFIEBCGOONCYZVMFQL3SYGX/events.json","paper":"https://pith.science/paper/XJ6UFIEB"},"agent_actions":{"view_html":"https://pith.science/pith/XJ6UFIEBCGOONCYZVMFQL3SYGX","download_json":"https://pith.science/pith/XJ6UFIEBCGOONCYZVMFQL3SYGX.json","view_paper":"https://pith.science/paper/XJ6UFIEB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.09391&json=true","fetch_graph":"https://pith.science/api/pith-number/XJ6UFIEBCGOONCYZVMFQL3SYGX/graph.json","fetch_events":"https://pith.science/api/pith-number/XJ6UFIEBCGOONCYZVMFQL3SYGX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XJ6UFIEBCGOONCYZVMFQL3SYGX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XJ6UFIEBCGOONCYZVMFQL3SYGX/action/storage_attestation","attest_author":"https://pith.science/pith/XJ6UFIEBCGOONCYZVMFQL3SYGX/action/author_attestation","sign_citation":"https://pith.science/pith/XJ6UFIEBCGOONCYZVMFQL3SYGX/action/citation_signature","submit_replication":"https://pith.science/pith/XJ6UFIEBCGOONCYZVMFQL3SYGX/action/replication_record"}},"created_at":"2026-07-05T04:16:24.072357+00:00","updated_at":"2026-07-05T04:16:24.072357+00:00"}