{"as_of":"2026-08-08T12:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:221679f9d9ba67a93eae51a431cbc025669e8e1c74b5c90a1394669c23e413a5","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T05:59:34.294487Z","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":"2026-05-22T22:32:12.966711Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2110.07831","last_updated":"2021-10-15T03:09:26Z","snapshot_observed_at":"2026-07-06T11:58:08.615915Z","submitted_at":"2021-10-15T03:09:26Z","title":"RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models","version":1},"cited_work":{"arxiv_id":"2110.07831","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.07831","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Rap: Robustness-aware perturbations for defending against backdoor attacks on nlp models","venue":null,"work_id":"085b6b87-9065-4621-8d9c-d5f9fe586ac6","year":2021},"citing_paper":{"arxiv_id":"2504.00446","last_updated":"2026-04-05T08:03:35Z","snapshot_observed_at":"2026-08-04T21:32:00.757719Z","submitted_at":"2025-04-01T05:58:14Z","title":"Exposing the Ghost in the Transformer: Abnormal Detection for Large Language Models via Hidden State Forensics","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-05-22T22:27:18.533162Z"},"links":{"cited_paper":"/paper/2110.07831","citing_paper":"/paper/2504.00446"},"observation_digest":"sha256:f13e76a6c3fba2fdd026b25c15e5d230d8d66b10e86590e0d5bd709752345ddb","observation_id":"b8439449-154b-4f34-aad4-6dd9f6288b5e","resolution":{"observed_at":"2026-05-22T22:32:12.969005Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2110.07831","last_updated":"2021-10-15T03:09:26Z","snapshot_observed_at":"2026-07-06T11:58:08.615915Z","submitted_at":"2021-10-15T03:09:26Z","title":"RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.07831","snapshot_observed_at":"2026-08-07T05:59:34.294487Z","title":"Ziqing Yang, Michael Backes, Yang Zhang, and Ahmed Salem","venue":null,"work_id":null,"year":2021},"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":46,"source":"pdf_text","source_observed_at":"2026-08-07T05:59:34.294487Z"},"links":{"cited_paper":"/paper/2110.07831","citing_paper":"/paper/2506.06518"},"observation_digest":"sha256:7f22199fbdafe9179de568aaa3a5e9986729463c5ffa3a23420709f47092673c","observation_id":"b6ac111a-005d-4f9f-ab65-c9bf547ee782","resolution":{"observed_at":"2026-08-07T05:59:34.294487Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.07831","last_updated":"2021-10-15T03:09:26Z","snapshot_observed_at":"2026-07-06T11:58:08.615915Z","submitted_at":"2021-10-15T03:09:26Z","title":"RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.07831","snapshot_observed_at":"2026-08-07T05:20:51.539219Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.08336","last_updated":"2025-06-11T01:39:01Z","snapshot_observed_at":"2026-08-07T22:32:21.983693Z","submitted_at":"2025-06-10T01:45:56Z","title":"Your Agent Can Defend Itself against Backdoor Attacks","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-07T05:20:51.539219Z"},"links":{"cited_paper":"/paper/2110.07831","citing_paper":"/paper/2506.08336"},"observation_digest":"sha256:6f22f2eb8f238c051773ecf0b49f911dfd6ebdd7af392c22f9ac4ba2b9390c86","observation_id":"acca5bd7-abbf-4f1d-ae87-a3ac034cccb7","resolution":{"observed_at":"2026-08-07T05:20:51.539219Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.07831","last_updated":"2021-10-15T03:09:26Z","snapshot_observed_at":"2026-07-06T11:58:08.615915Z","submitted_at":"2021-10-15T03:09:26Z","title":"RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.07831","snapshot_observed_at":"2026-08-05T14:42:31.539194Z","title":"Rap: Robustness-aware perturbations for de- fending against backdoor attacks on NLP models","venue":null,"work_id":null,"year":2021},"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":57,"source":"pdf_text","source_observed_at":"2026-08-05T14:42:31.539194Z"},"links":{"cited_paper":"/paper/2110.07831","citing_paper":"/paper/2508.21004"},"observation_digest":"sha256:a1b0246c83e1306e848e2cc02ab0bf51f597da3afc2a81b6edb004277aea389d","observation_id":"3b0c7527-3eaa-49d3-af59-51a7c0cb5075","resolution":{"observed_at":"2026-08-05T14:42:31.539194Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2110.07831/citation-record","integrity":"/paper/2110.07831/integrity","json":"/paper/2110.07831/citation-record.json","paper":"/paper/2110.07831"},"outbound":[],"paper":{"arxiv_id":"2110.07831","last_updated":"2021-10-15T03:09:26Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T11:58:08.615915Z","submitted_at":"2021-10-15T03:09:26Z","title":"RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP 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 4 inbound Pith citation observations for arXiv:2110.07831."}