{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AHNWU33ECEHQA5QHTFXPMCHKDY","short_pith_number":"pith:AHNWU33E","schema_version":"1.0","canonical_sha256":"01db6a6f64110f007607996ef608ea1e36544469139f934b74d3561027b9c066","source":{"kind":"arxiv","id":"2406.07217","version":2},"attestation_state":"computed","paper":{"title":"A Synthetic Dataset for Personal Attribute Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Hanna Yukhymenko, Mark Vero, Martin Vechev, Robin Staab","submitted_at":"2024-06-11T12:50:53Z","abstract_excerpt":"Recently, powerful Large Language Models (LLMs) have become easily accessible to hundreds of millions of users world-wide. However, their strong capabilities and vast world knowledge do not come without associated privacy risks. In this work, we focus on the emerging privacy threat LLMs pose -- the ability to accurately infer personal information from online texts. Despite the growing importance of LLM-based author profiling, research in this area has been hampered by a lack of suitable public datasets, largely due to ethical and privacy concerns associated with real personal data. We take two"},"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":"2406.07217","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-11T12:50:53Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"c00b570654ce6eade19d742771b78ff9de8ab8089ecfa63c7635779b56ec1886","abstract_canon_sha256":"9f1a5691746558e11c627df8f85f91ff51bf18643020adc9fc667d1cf4c8febb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:17.011554Z","signature_b64":"hFKqat5ync52Px3ltpBtdTbykWTLektXKZbAtqXcDOSQat3a3zDQ2tcTtGUhTMlZnkJYDZnE2mhq7oHPIe76Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01db6a6f64110f007607996ef608ea1e36544469139f934b74d3561027b9c066","last_reissued_at":"2026-07-05T09:30:17.011063Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:17.011063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Synthetic Dataset for Personal Attribute Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Hanna Yukhymenko, Mark Vero, Martin Vechev, Robin Staab","submitted_at":"2024-06-11T12:50:53Z","abstract_excerpt":"Recently, powerful Large Language Models (LLMs) have become easily accessible to hundreds of millions of users world-wide. However, their strong capabilities and vast world knowledge do not come without associated privacy risks. In this work, we focus on the emerging privacy threat LLMs pose -- the ability to accurately infer personal information from online texts. Despite the growing importance of LLM-based author profiling, research in this area has been hampered by a lack of suitable public datasets, largely due to ethical and privacy concerns associated with real personal data. We take two"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07217","kind":"arxiv","version":2},"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/2406.07217/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":"2406.07217","created_at":"2026-07-05T09:30:17.011127+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.07217v2","created_at":"2026-07-05T09:30:17.011127+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07217","created_at":"2026-07-05T09:30:17.011127+00:00"},{"alias_kind":"pith_short_12","alias_value":"AHNWU33ECEHQ","created_at":"2026-07-05T09:30:17.011127+00:00"},{"alias_kind":"pith_short_16","alias_value":"AHNWU33ECEHQA5QH","created_at":"2026-07-05T09:30:17.011127+00:00"},{"alias_kind":"pith_short_8","alias_value":"AHNWU33E","created_at":"2026-07-05T09:30:17.011127+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.07486","citing_title":"Private Seeds, Public LLMs: Realistic and Privacy-Preserving Synthetic Data Generation","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AHNWU33ECEHQA5QHTFXPMCHKDY","json":"https://pith.science/pith/AHNWU33ECEHQA5QHTFXPMCHKDY.json","graph_json":"https://pith.science/api/pith-number/AHNWU33ECEHQA5QHTFXPMCHKDY/graph.json","events_json":"https://pith.science/api/pith-number/AHNWU33ECEHQA5QHTFXPMCHKDY/events.json","paper":"https://pith.science/paper/AHNWU33E"},"agent_actions":{"view_html":"https://pith.science/pith/AHNWU33ECEHQA5QHTFXPMCHKDY","download_json":"https://pith.science/pith/AHNWU33ECEHQA5QHTFXPMCHKDY.json","view_paper":"https://pith.science/paper/AHNWU33E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.07217&json=true","fetch_graph":"https://pith.science/api/pith-number/AHNWU33ECEHQA5QHTFXPMCHKDY/graph.json","fetch_events":"https://pith.science/api/pith-number/AHNWU33ECEHQA5QHTFXPMCHKDY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AHNWU33ECEHQA5QHTFXPMCHKDY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AHNWU33ECEHQA5QHTFXPMCHKDY/action/storage_attestation","attest_author":"https://pith.science/pith/AHNWU33ECEHQA5QHTFXPMCHKDY/action/author_attestation","sign_citation":"https://pith.science/pith/AHNWU33ECEHQA5QHTFXPMCHKDY/action/citation_signature","submit_replication":"https://pith.science/pith/AHNWU33ECEHQA5QHTFXPMCHKDY/action/replication_record"}},"created_at":"2026-07-05T09:30:17.011127+00:00","updated_at":"2026-07-05T09:30:17.011127+00:00"}