{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BSZVHPZE6NIMLN3L2F3WLNMUPQ","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":"27fc24651a76c7b39e247228abb213c2dc363fd0c71204d6ccd0881d0cce7eef","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-10T08:03:41Z","title_canon_sha256":"ab067326313299037b653930c5de816e3c4ad156d07bf4784b69e5e27a45520b"},"schema_version":"1.0","source":{"id":"2307.04401","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.04401","created_at":"2026-07-05T06:29:12Z"},{"alias_kind":"arxiv_version","alias_value":"2307.04401v1","created_at":"2026-07-05T06:29:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.04401","created_at":"2026-07-05T06:29:12Z"},{"alias_kind":"pith_short_12","alias_value":"BSZVHPZE6NIM","created_at":"2026-07-05T06:29:12Z"},{"alias_kind":"pith_short_16","alias_value":"BSZVHPZE6NIMLN3L","created_at":"2026-07-05T06:29:12Z"},{"alias_kind":"pith_short_8","alias_value":"BSZVHPZE","created_at":"2026-07-05T06:29:12Z"}],"graph_snapshots":[{"event_id":"sha256:b65697c622e8bbdf7ab1d97acbde563c0596aca01b18ce72e3ae063a8db45135","target":"graph","created_at":"2026-07-05T06:29:12Z","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/2307.04401/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large pre-trained language models achieve impressive results across many tasks. However, recent works point out that pre-trained language models may memorize a considerable fraction of their training data, leading to the privacy risk of information leakage. In this paper, we propose a method named Ethicist for targeted training data extraction through loss smoothed soft prompting and calibrated confidence estimation, investigating how to recover the suffix in the training data when given a prefix. To elicit memorization in the attacked model, we tune soft prompt embeddings while keeping the mo","authors_text":"Jiaxin Wen, Minlie Huang, Zhexin Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-10T08:03:41Z","title":"Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.04401","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":"sha256:3c170c0277f7e7a5b64020445e163e8d80c382d7c240660d2d226f400c81c98c","target":"record","created_at":"2026-07-05T06:29:12Z","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":"27fc24651a76c7b39e247228abb213c2dc363fd0c71204d6ccd0881d0cce7eef","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-10T08:03:41Z","title_canon_sha256":"ab067326313299037b653930c5de816e3c4ad156d07bf4784b69e5e27a45520b"},"schema_version":"1.0","source":{"id":"2307.04401","kind":"arxiv","version":1}},"canonical_sha256":"0cb353bf24f350c5b76bd17765b5947c30c88c55e3d70ea937e33bdafaad6ec0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0cb353bf24f350c5b76bd17765b5947c30c88c55e3d70ea937e33bdafaad6ec0","first_computed_at":"2026-07-05T06:29:12.689905Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:29:12.689905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QUe63c3MAfEZZ8iZV9uPU1T4q+YsL9lC5h0mQAV5JtH75/loED6+2HlbFnouxCyl0wrtwgVeyoo1PZ1D8+gADQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:29:12.690377Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.04401","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c170c0277f7e7a5b64020445e163e8d80c382d7c240660d2d226f400c81c98c","sha256:b65697c622e8bbdf7ab1d97acbde563c0596aca01b18ce72e3ae063a8db45135"],"state_sha256":"91b87aad4df8b94f50182e16692dcaa9689464b3b772133974c7b7f58d430635"}