{"as_of":"2026-08-09T17:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fa2a3204b25f2991c7a9b10513d067f1c4da9f5002cc435d878181cf17c32cff","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":"2026-08-09T00:50:00.774159Z","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":"2026-05-11T21:46:35.204845Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.12168","last_updated":"2024-03-29T12:12:30Z","snapshot_observed_at":"2026-08-06T19:16:12.768633Z","submitted_at":"2024-02-19T14:22:54Z","title":"Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.12168","snapshot_observed_at":"2026-08-09T00:50:00.774159Z","title":"Defending against weight-poisoning backdoor attacks for parameter-efficient fine-tuning,","venue":null,"work_id":null,"year":2024},"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":179,"source":"pdf_text","source_observed_at":"2026-08-09T00:50:00.774159Z"},"links":{"cited_paper":"/paper/2402.12168","citing_paper":"/paper/2502.05224"},"observation_digest":"sha256:77cd3863e160d36c98059b4147001e5286f488570577affc23537b5de40ff51f","observation_id":"c2089771-eff6-4feb-84fc-d2532b7c7a5f","resolution":{"observed_at":"2026-08-09T00:50:00.774159Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.12168","last_updated":"2024-03-29T12:12:30Z","snapshot_observed_at":"2026-08-06T19:16:12.768633Z","submitted_at":"2024-02-19T14:22:54Z","title":"Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.12168","snapshot_observed_at":"2026-08-08T17:43:24.844859Z","title":"Defending against weight-poisoning backdoor attacks for parameter-efficient fine-tuning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.06892","last_updated":"2025-02-09T12:03:59Z","snapshot_observed_at":"2026-08-09T11:22:28.299850Z","submitted_at":"2025-02-09T12:03:59Z","title":"Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-08T17:43:24.844859Z"},"links":{"cited_paper":"/paper/2402.12168","citing_paper":"/paper/2502.06892"},"observation_digest":"sha256:897328197c09fa03361f9eb2845b93b366b52240dccc5f0d3be04b397de9a600","observation_id":"9909c6b8-19a9-45bd-92c7-d908ade9326e","resolution":{"observed_at":"2026-08-08T17:43:24.844859Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.12168","last_updated":"2024-03-29T12:12:30Z","snapshot_observed_at":"2026-08-06T19:16:12.768633Z","submitted_at":"2024-02-19T14:22:54Z","title":"Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.12168","snapshot_observed_at":"2026-08-05T14:42:31.558204Z","title":"De- fending against weight-poisoning backdoor attacks for parameter-efficient fine-tuning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.21004","last_updated":"2025-08-28T17:05:18Z","snapshot_observed_at":"2026-08-07T06:34:15.037429Z","submitted_at":"2025-08-28T17:05:18Z","title":"Lethe: Purifying Backdoored Large Language Models with Knowledge Dilution","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-05T14:42:31.558204Z"},"links":{"cited_paper":"/paper/2402.12168","citing_paper":"/paper/2508.21004"},"observation_digest":"sha256:3cb00d62549b0477a8156c25b645fc4539f993339c6a44edfe00b5d02c57a342","observation_id":"dd53e15a-c0e7-48ba-97b1-c0bff164a097","resolution":{"observed_at":"2026-08-05T14:42:31.558204Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.12168","last_updated":"2024-03-29T12:12:30Z","snapshot_observed_at":"2026-08-06T19:16:12.768633Z","submitted_at":"2024-02-19T14:22:54Z","title":"Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning","version":3},"cited_work":{"arxiv_id":"2402.12168","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.12168","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Defending against weight-poisoning backdoor attacks for parameter-efficient fine-tuning","venue":null,"work_id":"8c46c79e-4260-4500-aafd-e0406184ccf8","year":2024},"citing_paper":{"arxiv_id":"2604.04738","last_updated":"2026-07-07T04:10:46Z","snapshot_observed_at":"2026-08-04T02:10:20.384292Z","submitted_at":"2026-04-06T15:04:27Z","title":"Fine-Tuning Integrity for Modern Neural Networks: Structured Drift Proofs via Norm, Rank, and Sparsity Certificates","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-10T19:40:25.318694Z"},"links":{"cited_paper":"/paper/2402.12168","citing_paper":"/paper/2604.04738"},"observation_digest":"sha256:c2cb2c21b1af210106aac1dd2c14ffcab7baf3dc15aeb7af9022177c2efa7e8f","observation_id":"0a9e253d-44cc-47f1-ba57-954dc7b0063a","resolution":{"observed_at":"2026-05-10T22:35:52.782863Z","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":"2402.12168","last_updated":"2024-03-29T12:12:30Z","snapshot_observed_at":"2026-08-06T19:16:12.768633Z","submitted_at":"2024-02-19T14:22:54Z","title":"Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.12168","snapshot_observed_at":"2026-07-13T09:41:56.414542Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2604.04738","last_updated":"2026-07-07T04:10:46Z","snapshot_observed_at":"2026-08-04T02:10:20.384292Z","submitted_at":"2026-04-06T15:04:27Z","title":"Fine-Tuning Integrity for Modern Neural Networks: Structured Drift Proofs via Norm, Rank, and Sparsity Certificates","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-07-13T09:41:56.414542Z"},"links":{"cited_paper":"/paper/2402.12168","citing_paper":"/paper/2604.04738"},"observation_digest":"sha256:31e3eaa52541c7e756aed8122fda76c5bac7f2e6045b9e295da1e14d86f3fa2b","observation_id":"528ff828-b1f3-439b-a2b1-8ca036da4e72","resolution":{"observed_at":"2026-07-13T09:41:56.414542Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.12168","last_updated":"2024-03-29T12:12:30Z","snapshot_observed_at":"2026-08-06T19:16:12.768633Z","submitted_at":"2024-02-19T14:22:54Z","title":"Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning","version":3},"cited_work":{"arxiv_id":"2402.12168","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.12168","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Defending against weight-poisoning backdoor attacks for parameter-efficient fine-tuning","venue":null,"work_id":"8c46c79e-4260-4500-aafd-e0406184ccf8","year":2024},"citing_paper":{"arxiv_id":"2604.24350","last_updated":"2026-04-27T11:44:42Z","snapshot_observed_at":"2026-07-06T23:10:24.992210Z","submitted_at":"2026-04-27T11:44:42Z","title":"Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Training","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-05-08T04:29:11.570861Z"},"links":{"cited_paper":"/paper/2402.12168","citing_paper":"/paper/2604.24350"},"observation_digest":"sha256:8f864892ba6340b50e27741cc0f4a99fd68f3f425ca2b60ff0f32d399a8581e3","observation_id":"995d8c02-d0ec-4ad6-9ed3-e87462ddcb7a","resolution":{"observed_at":"2026-05-11T21:46:35.222998Z","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/2402.12168/citation-record","integrity":"/paper/2402.12168/integrity","json":"/paper/2402.12168/citation-record.json","paper":"/paper/2402.12168"},"outbound":[],"paper":{"arxiv_id":"2402.12168","last_updated":"2024-03-29T12:12:30Z","latest_version":3,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-06T19:16:12.768633Z","submitted_at":"2024-02-19T14:22:54Z","title":"Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning"},"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:2402.12168."}