{"as_of":"2026-08-09T16:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fe7d64d93c34b03ba9b50e06cd92bd586179035949f58bf93b8b789d8a68a710","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":"2026-08-09T06:31:02.800959+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":"2026-08-09T00:50:00.836199Z","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":"2026-06-29T13:43:28.414072Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2110.03735","last_updated":"2022-02-06T21:26:28Z","snapshot_observed_at":"2026-07-06T11:55:35.648043Z","submitted_at":"2021-10-07T18:32:54Z","title":"Adversarial Unlearning of Backdoors via Implicit Hypergradient","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.03735","snapshot_observed_at":"2026-08-09T00:50:00.836199Z","title":"Adversarial unlearning of backdoors via implicit hypergradient,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.05224","last_updated":"2025-02-06T04:43:05Z","snapshot_observed_at":"2026-08-09T05:58:57.244749Z","submitted_at":"2025-02-06T04:43:05Z","title":"A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations","version":1},"reference_index":193,"source":"pdf_text","source_observed_at":"2026-08-09T00:50:00.836199Z"},"links":{"cited_paper":"/paper/2110.03735","citing_paper":"/paper/2502.05224"},"observation_digest":"sha256:4c6a9ea9d0c5663ce0c7e68bde44990dfd8ca27da840b36e52080680c55ce267","observation_id":"ecea245d-8e55-4894-a7e6-d4f7b938c00d","resolution":{"observed_at":"2026-08-09T00:50:00.836199Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.03735","last_updated":"2022-02-06T21:26:28Z","snapshot_observed_at":"2026-07-06T11:55:35.648043Z","submitted_at":"2021-10-07T18:32:54Z","title":"Adversarial Unlearning of Backdoors via Implicit Hypergradient","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.03735","snapshot_observed_at":"2026-08-07T15:25:23.263769Z","title":"Adversarial unlearning of backdoors via implicit hypergradient,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.15308","last_updated":"2025-05-21T09:36:35Z","snapshot_observed_at":"2026-08-07T15:18:07.516589Z","submitted_at":"2025-05-21T09:36:35Z","title":"BadSR: Stealthy Label Backdoor Attacks on Image Super-Resolution","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T15:25:23.263769Z"},"links":{"cited_paper":"/paper/2110.03735","citing_paper":"/paper/2505.15308"},"observation_digest":"sha256:3413fc2ef9d931b56cd79b6718df33cd1600129343b2c8b3bc83f3bdad1d995a","observation_id":"4df6d6a7-571a-4ec1-938f-618c58a6c83d","resolution":{"observed_at":"2026-08-07T15:25:23.263769Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.03735","last_updated":"2022-02-06T21:26:28Z","snapshot_observed_at":"2026-07-06T11:55:35.648043Z","submitted_at":"2021-10-07T18:32:54Z","title":"Adversarial Unlearning of Backdoors via Implicit Hypergradient","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.03735","snapshot_observed_at":"2026-08-06T17:33:52.804575Z","title":"Adversarial unlearning of backdoors via implicit hypergradient","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-06T17:27:09.347274Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:52.804575Z"},"links":{"cited_paper":"/paper/2110.03735","citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:f4e82e586f2eb3471d57d80407b5926ecf65d416dff729ac0ceb398a69f09162","observation_id":"c112a32a-9fff-4865-955a-8573fb044fe0","resolution":{"observed_at":"2026-08-06T17:33:52.804575Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.03735","last_updated":"2022-02-06T21:26:28Z","snapshot_observed_at":"2026-07-06T11:55:35.648043Z","submitted_at":"2021-10-07T18:32:54Z","title":"Adversarial Unlearning of Backdoors via Implicit Hypergradient","version":4},"cited_work":{"arxiv_id":"2110.03735","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.03735","snapshot_observed_at":"2026-06-29T13:43:28.414072Z","title":"Sampdetox: Black-box backdoor defense via perturbation-based sample detoxification.NeurIPS, 37:121236–121264, 2024b","venue":null,"work_id":"0472ded8-f2de-4e7d-a6be-e0b36e35b47a","year":2021},"citing_paper":{"arxiv_id":"2601.21692","last_updated":"2026-05-22T01:46:45Z","snapshot_observed_at":"2026-08-02T10:02:20.704165Z","submitted_at":"2026-01-29T13:26:29Z","title":"TCAP: Tri-Component Attention Profiling for Unsupervised Backdoor Detection in MLLM Fine-Tuning","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-25T07:33:15.865358Z"},"links":{"cited_paper":"/paper/2110.03735","citing_paper":"/paper/2601.21692"},"observation_digest":"sha256:b6121b42bb51f13f4b11bdb4e0011b7aae015006e83ed91efbf39f8ab298feca","observation_id":"63d56bea-fec3-4268-a795-747251c74ee1","resolution":{"observed_at":"2026-05-25T07:35:28.664465Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.03735","last_updated":"2022-02-06T21:26:28Z","snapshot_observed_at":"2026-07-06T11:55:35.648043Z","submitted_at":"2021-10-07T18:32:54Z","title":"Adversarial Unlearning of Backdoors via Implicit Hypergradient","version":4},"cited_work":{"arxiv_id":"2110.03735","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.03735","snapshot_observed_at":"2026-06-29T13:43:28.414072Z","title":"Sampdetox: Black-box backdoor defense via perturbation-based sample detoxification.NeurIPS, 37:121236–121264, 2024b","venue":null,"work_id":"0472ded8-f2de-4e7d-a6be-e0b36e35b47a","year":2021},"citing_paper":{"arxiv_id":"2604.24162","last_updated":"2026-04-27T08:18:30Z","snapshot_observed_at":"2026-07-06T23:10:16.426836Z","submitted_at":"2026-04-27T08:18:30Z","title":"Defusing the Trigger: Plug-and-Play Defense for Backdoored LLMs via Tail-Risk Intrinsic Geometric Smoothing","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-05-08T03:09:43.879809Z"},"links":{"cited_paper":"/paper/2110.03735","citing_paper":"/paper/2604.24162"},"observation_digest":"sha256:319fa2f8e4c1efcb79c03a9a43d6929ae9b66b81b54ad156c64fb21d56fdf866","observation_id":"dec3c917-93eb-4717-b4a6-b2881471446a","resolution":{"observed_at":"2026-05-11T22:16:23.476876Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.03735","last_updated":"2022-02-06T21:26:28Z","snapshot_observed_at":"2026-07-06T11:55:35.648043Z","submitted_at":"2021-10-07T18:32:54Z","title":"Adversarial Unlearning of Backdoors via Implicit Hypergradient","version":4},"cited_work":{"arxiv_id":"2110.03735","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.03735","snapshot_observed_at":"2026-06-29T13:43:28.414072Z","title":"Sampdetox: Black-box backdoor defense via perturbation-based sample detoxification.NeurIPS, 37:121236–121264, 2024b","venue":null,"work_id":"0472ded8-f2de-4e7d-a6be-e0b36e35b47a","year":2021},"citing_paper":{"arxiv_id":"2605.27809","last_updated":"2026-05-28T17:28:34Z","snapshot_observed_at":"2026-08-03T05:40:01.499964Z","submitted_at":"2026-05-27T01:02:49Z","title":"Density-aware Sample-specific Attack","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-06-29T13:43:07.407298Z"},"links":{"cited_paper":"/paper/2110.03735","citing_paper":"/paper/2605.27809"},"observation_digest":"sha256:f7360ed4deb6e1ca7f46f4821b6bec54bceb8b2ad06ef1a8aabad88f5b6f7784","observation_id":"02018899-bcc9-4bd4-9957-d05a73076ae5","resolution":{"observed_at":"2026-06-29T13:43:28.415965Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2110.03735/citation-record","integrity":"/paper/2110.03735/integrity","json":"/paper/2110.03735/citation-record.json","paper":"/paper/2110.03735"},"outbound":[],"paper":{"arxiv_id":"2110.03735","last_updated":"2022-02-06T21:26:28Z","latest_version":4,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T11:55:35.648043Z","submitted_at":"2021-10-07T18:32:54Z","title":"Adversarial Unlearning of Backdoors via Implicit Hypergradient"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 6 inbound Pith citation observations for arXiv:2110.03735."}