{"as_of":"2026-08-08T09:31:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d1c6804619c8fdb55cf3bbb48869ab9579348034c18cc1f7d7cb52d2f553b73e","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":6,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":6,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":6,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":6,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T10:27:49.683237Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-01T09:25:40.834864Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2404.01231","last_updated":"2024-04-01T16:50:54Z","snapshot_observed_at":"2026-07-06T17:54:03.923842Z","submitted_at":"2024-04-01T16:50:54Z","title":"Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.01231","snapshot_observed_at":"2026-08-07T10:27:49.683237Z","title":"Detecting, explaining, and mitigating memo- rization in diffusion models","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2506.05198","last_updated":"2025-06-05T16:10:47Z","snapshot_observed_at":"2026-08-07T18:04:06.884523Z","submitted_at":"2025-06-05T16:10:47Z","title":"Quantifying Cross-Modality Memorization in Vision-Language Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T10:27:49.683237Z"},"links":{"cited_paper":"/paper/2404.01231","citing_paper":"/paper/2506.05198"},"observation_digest":"sha256:1b7beeb13d2357d02e879dfefe82ac1cb3c0c56bddee568a5b36cdfaea7f04b7","observation_id":"bc4530e6-94f6-4ced-878f-07503ae1f9d4","resolution":{"observed_at":"2026-08-07T10:27:49.683237Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.01231","last_updated":"2024-04-01T16:50:54Z","snapshot_observed_at":"2026-07-06T17:54:03.923842Z","submitted_at":"2024-04-01T16:50:54Z","title":"Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.01231","snapshot_observed_at":"2026-08-07T05:59:33.836732Z","title":"Jason E Weston","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06518","last_updated":"2025-06-06T20:32:43Z","snapshot_observed_at":"2026-08-07T05:52:43.506241Z","submitted_at":"2025-06-06T20:32:43Z","title":"A Systematic Review of Poisoning Attacks Against Large Language Models","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T05:59:33.836732Z"},"links":{"cited_paper":"/paper/2404.01231","citing_paper":"/paper/2506.06518"},"observation_digest":"sha256:77e3e87756739b58e391b7c76bb098fedcfd545f72ee9ac6a0a04002eccd935e","observation_id":"9e05af27-1a3e-4953-aa2b-6090027ce4e0","resolution":{"observed_at":"2026-08-07T05:59:33.836732Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.01231","last_updated":"2024-04-01T16:50:54Z","snapshot_observed_at":"2026-07-06T17:54:03.923842Z","submitted_at":"2024-04-01T16:50:54Z","title":"Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.01231","snapshot_observed_at":"2026-08-06T21:23:39.710949Z","title":"Privacy back- doors: Enhancing membership inference through poisoning pre-trained models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.00423","last_updated":"2025-07-01T04:46:23Z","snapshot_observed_at":"2026-08-07T19:56:39.809065Z","submitted_at":"2025-07-01T04:46:23Z","title":"Find a Scapegoat: Poisoning Membership Inference Attack and Defense to Federated Learning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T21:23:39.710949Z"},"links":{"cited_paper":"/paper/2404.01231","citing_paper":"/paper/2507.00423"},"observation_digest":"sha256:eb256494796b722239a42eada408fb43026c340aefb2110178b3e69a2f771d7f","observation_id":"a28e3ae1-e3bf-4518-9e47-725b547b0177","resolution":{"observed_at":"2026-08-06T21:23:39.710949Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.01231","last_updated":"2024-04-01T16:50:54Z","snapshot_observed_at":"2026-07-06T17:54:03.923842Z","submitted_at":"2024-04-01T16:50:54Z","title":"Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.01231","snapshot_observed_at":"2026-08-06T19:55:22.345690Z","title":"Privacy backdoors: Enhancing membership inference through poisoning pre-trained models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.04457","last_updated":"2025-07-06T16:35:48Z","snapshot_observed_at":"2026-08-06T19:44:46.263081Z","submitted_at":"2025-07-06T16:35:48Z","title":"UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:22.345690Z"},"links":{"cited_paper":"/paper/2404.01231","citing_paper":"/paper/2507.04457"},"observation_digest":"sha256:1dcc74b9b8a891277ec52913e8f6f20c7bafc2c29338dd8f1aab9d88a4a3baf6","observation_id":"243ac1f8-b04f-4db5-83eb-4ca76a754df5","resolution":{"observed_at":"2026-08-06T19:55:22.345690Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.01231","last_updated":"2024-04-01T16:50:54Z","snapshot_observed_at":"2026-07-06T17:54:03.923842Z","submitted_at":"2024-04-01T16:50:54Z","title":"Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models","version":1},"cited_work":{"arxiv_id":"2404.01231","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.01231","snapshot_observed_at":"2026-07-01T09:25:40.834864Z","title":"arXiv preprint arXiv:2404.01231 , year=","venue":null,"work_id":"ceff817f-c250-4bd8-ae6e-669522367547","year":2024},"citing_paper":{"arxiv_id":"2605.26133","last_updated":"2026-05-21T10:32:33Z","snapshot_observed_at":"2026-08-07T10:44:40.983544Z","submitted_at":"2026-05-21T10:32:33Z","title":"Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security Implications","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-06-30T17:20:16.735285Z"},"links":{"cited_paper":"/paper/2404.01231","citing_paper":"/paper/2605.26133"},"observation_digest":"sha256:bf218f4e146ace3cc2c0b196450bbd5af8fc36a2c42d57061e023b07a377adba","observation_id":"0cc5d97b-10cb-49cc-9440-bcf92ddecb6f","resolution":{"observed_at":"2026-06-30T17:24:57.252080Z","resolver_source":"arxiv_id","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.01231","last_updated":"2024-04-01T16:50:54Z","snapshot_observed_at":"2026-07-06T17:54:03.923842Z","submitted_at":"2024-04-01T16:50:54Z","title":"Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models","version":1},"cited_work":{"arxiv_id":"2404.01231","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.01231","snapshot_observed_at":"2026-07-01T09:25:40.834864Z","title":"arXiv preprint arXiv:2404.01231 , year=","venue":null,"work_id":"ceff817f-c250-4bd8-ae6e-669522367547","year":2024},"citing_paper":{"arxiv_id":"2606.31208","last_updated":"2026-06-30T06:40:36Z","snapshot_observed_at":"2026-08-01T15:26:30.335537Z","submitted_at":"2026-06-30T06:40:36Z","title":"Probing Memorization of Tabular In-Context Learning","version":1},"reference_index":103,"source":"arxiv_source","source_observed_at":"2026-07-01T06:37:44.328625Z"},"links":{"cited_paper":"/paper/2404.01231","citing_paper":"/paper/2606.31208"},"observation_digest":"sha256:52b75ce7b015ea2c29545d314ee3cf42f5df085738ad8bcbacbc88beb6613e0b","observation_id":"e546d5e6-17cb-41b3-96dc-848364ffa5c5","resolution":{"observed_at":"2026-07-01T09:25:40.837030Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2404.01231/citation-record","integrity":"/paper/2404.01231/integrity","json":"/paper/2404.01231/citation-record.json","paper":"/paper/2404.01231"},"outbound":[],"paper":{"arxiv_id":"2404.01231","last_updated":"2024-04-01T16:50:54Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-07-06T17:54:03.923842Z","submitted_at":"2024-04-01T16:50:54Z","title":"Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 6 inbound Pith citation observations for arXiv:2404.01231."}