{"as_of":"2026-08-18T02:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:20643c6767423ccec30ebe63fa0ff8d4f9ea9869dce9c63cc9c199625f839e05","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":5,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":5,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":5,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":5,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T23:40:19.205513Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-05T18:12:38.765761Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2307.04401","last_updated":"2023-07-10T08:03:41Z","snapshot_observed_at":"2026-08-16T15:17:32.447656Z","submitted_at":"2023-07-10T08:03:41Z","title":"Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.04401","snapshot_observed_at":"2026-08-10T23:40:19.205513Z","title":", author Wen, J","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.20087","last_updated":"2024-12-28T09:08:37Z","snapshot_observed_at":"2026-08-15T12:46:32.785416Z","submitted_at":"2024-12-28T09:08:37Z","title":"On the Validity of Traditional Vulnerability Scoring Systems for Adversarial Attacks against LLMs","version":1},"reference_index":162,"source":"arxiv_source","source_observed_at":"2026-08-10T23:40:19.205513Z"},"links":{"cited_paper":"/paper/2307.04401","citing_paper":"/paper/2412.20087"},"observation_digest":"sha256:a4f975cafa2af9826181902a1abe9890271cda28318174f3d435c8a879aeca95","observation_id":"364ec7c8-97db-4b9f-be13-942158f325aa","resolution":{"observed_at":"2026-08-10T23:40:19.205513Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.04401","last_updated":"2023-07-10T08:03:41Z","snapshot_observed_at":"2026-08-16T15:17:32.447656Z","submitted_at":"2023-07-10T08:03:41Z","title":"Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.04401","snapshot_observed_at":"2026-08-09T10:29:50.004481Z","title":"Ethicist: Targeted training data extraction through loss smoothed soft prompting and calibrated confidence estimation,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.02960","last_updated":"2025-02-05T07:54:07Z","snapshot_observed_at":"2026-08-11T14:26:02.458624Z","submitted_at":"2025-02-05T07:54:07Z","title":"Large Language Model Adversarial Landscape Through the Lens of Attack Objectives","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-09T10:29:50.004481Z"},"links":{"cited_paper":"/paper/2307.04401","citing_paper":"/paper/2502.02960"},"observation_digest":"sha256:848655bde93c649a15f1d4b9a4d1f027a6015e4e87fc6fa9e00831d66fce9226","observation_id":"e7a9df9f-6b17-49af-a957-e5366528a70c","resolution":{"observed_at":"2026-08-09T10:29:50.004481Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.04401","last_updated":"2023-07-10T08:03:41Z","snapshot_observed_at":"2026-08-16T15:17:32.447656Z","submitted_at":"2023-07-10T08:03:41Z","title":"Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.04401","snapshot_observed_at":"2026-08-07T00:46:10.546530Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.12699","last_updated":"2025-06-19T06:30:24Z","snapshot_observed_at":"2026-08-14T17:40:51.768214Z","submitted_at":"2025-06-15T03:14:03Z","title":"SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation","version":2},"reference_index":156,"source":"pdf_text","source_observed_at":"2026-08-07T00:46:10.546530Z"},"links":{"cited_paper":"/paper/2307.04401","citing_paper":"/paper/2506.12699"},"observation_digest":"sha256:ee1f93eaa43a71bccae08270d4d4304cbe3906a3704f09a50505d6be9bdf7999","observation_id":"1c195647-b3af-43cd-adb7-0ae745e1f4ff","resolution":{"observed_at":"2026-08-07T00:46:10.546530Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.04401","last_updated":"2023-07-10T08:03:41Z","snapshot_observed_at":"2026-08-16T15:17:32.447656Z","submitted_at":"2023-07-10T08:03:41Z","title":"Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.04401","snapshot_observed_at":"2026-08-06T22:23:15.392554Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.22521","last_updated":"2025-06-26T22:02:01Z","snapshot_observed_at":"2026-08-17T10:14:30.703303Z","submitted_at":"2025-06-26T22:02:01Z","title":"A Survey on Model Extraction Attacks and Defenses for Large Language Models","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-06T22:23:15.392554Z"},"links":{"cited_paper":"/paper/2307.04401","citing_paper":"/paper/2506.22521"},"observation_digest":"sha256:8e579fb8d688a0316c46267e1fa18db7e770f3db9b69b08b9dabe51cdab577a7","observation_id":"227c6367-f520-45d9-be7c-385f467585e9","resolution":{"observed_at":"2026-08-06T22:23:15.392554Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.04401","last_updated":"2023-07-10T08:03:41Z","snapshot_observed_at":"2026-08-16T15:17:32.447656Z","submitted_at":"2023-07-10T08:03:41Z","title":"Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation","version":1},"cited_work":{"arxiv_id":"2307.04401","doi":null,"metadata_source":"pith","pith_arxiv_id":"2307.04401","snapshot_observed_at":"2026-08-05T18:12:38.765761Z","title":"Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation","venue":"cs.CL","work_id":"355da29e-84d0-4709-85d9-0dc1ee257556","year":2023},"citing_paper":{"arxiv_id":"2508.15031","last_updated":"2025-08-27T05:10:26Z","snapshot_observed_at":"2026-08-14T23:52:31.572833Z","submitted_at":"2025-08-20T19:49:59Z","title":"A Systematic Survey of Model Extraction Attacks and Defenses: State-of-the-Art and Perspectives","version":2},"reference_index":261,"source":"pdf_text","source_observed_at":"2026-08-05T18:12:38.405633Z"},"links":{"cited_paper":"/paper/2307.04401","citing_paper":"/paper/2508.15031"},"observation_digest":"sha256:5970262b622c1494ad493cbe1665e27a9c4685f2ea1802e995989f8253e9929f","observation_id":"195a96e3-ad03-45d8-8815-45411d2de3ed","resolution":{"observed_at":"2026-08-05T18:12:38.771416Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2307.04401/citation-record","integrity":"/paper/2307.04401/integrity","json":"/paper/2307.04401/citation-record.json","paper":"/paper/2307.04401"},"outbound":[],"paper":{"arxiv_id":"2307.04401","last_updated":"2023-07-10T08:03:41Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T15:17:32.447656Z","submitted_at":"2023-07-10T08:03:41Z","title":"Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 5 inbound Pith citation observations for arXiv:2307.04401."}