{"as_of":"2026-08-07T23:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ca1bce3f357481cd272df4a069fbe46978d209459f64333a77e1b5619030c7eb","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T14:27:03.532090Z","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":"2026-05-11T13:11:05.821591Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.09798","last_updated":"2025-05-10T02:36:13Z","snapshot_observed_at":"2026-08-04T21:08:03.374081Z","submitted_at":"2025-01-16T19:01:25Z","title":"Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.09798","snapshot_observed_at":"2026-08-07T14:27:03.532090Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.18889","last_updated":"2025-08-24T03:15:13Z","snapshot_observed_at":"2026-08-07T14:21:41.034177Z","submitted_at":"2025-05-24T22:22:43Z","title":"Security Concerns for Large Language Models: A Survey","version":5},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T14:27:03.532090Z"},"links":{"cited_paper":"/paper/2501.09798","citing_paper":"/paper/2505.18889"},"observation_digest":"sha256:5aa0e408133128546b03791b4f2939804e0d58342bdfca3f761b8fce733cb097","observation_id":"30fba0b6-0662-48c2-9a97-08c7f135c1c9","resolution":{"observed_at":"2026-08-07T14:27:03.532090Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.09798","last_updated":"2025-05-10T02:36:13Z","snapshot_observed_at":"2026-08-04T21:08:03.374081Z","submitted_at":"2025-01-16T19:01:25Z","title":"Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface","version":2},"cited_work":{"arxiv_id":"2501.09798","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.09798","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Pandya, Ashish Hooda, Xiaohan Fu, and Earlence Fernandes","venue":null,"work_id":"0989ea79-414e-410f-a173-c189f2b46df3","year":2025},"citing_paper":{"arxiv_id":"2604.16845","last_updated":"2026-04-18T05:28:53Z","snapshot_observed_at":"2026-07-06T23:04:05.813982Z","submitted_at":"2026-04-18T05:28:53Z","title":"DART: Mitigating Harm Drift in Difference-Aware LLMs via Distill-Audit-Repair Training","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-10T07:18:49.076088Z"},"links":{"cited_paper":"/paper/2501.09798","citing_paper":"/paper/2604.16845"},"observation_digest":"sha256:f953713e8c5e518722a09ea1205de821485fc94476a7efb525411b6407fe5c51","observation_id":"b58182b9-d6e6-4d72-b42b-41026ce39bb6","resolution":{"observed_at":"2026-05-10T07:26:59.924242Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.09798","last_updated":"2025-05-10T02:36:13Z","snapshot_observed_at":"2026-08-04T21:08:03.374081Z","submitted_at":"2025-01-16T19:01:25Z","title":"Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface","version":2},"cited_work":{"arxiv_id":"2501.09798","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.09798","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Pandya, Ashish Hooda, Xiaohan Fu, and Earlence Fernandes","venue":null,"work_id":"0989ea79-414e-410f-a173-c189f2b46df3","year":2025},"citing_paper":{"arxiv_id":"2604.19657","last_updated":"2026-04-21T16:45:30Z","snapshot_observed_at":"2026-07-06T23:06:16.972438Z","submitted_at":"2026-04-21T16:45:30Z","title":"An AI Agent Execution Environment to Safeguard User Data","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-10T02:14:40.639143Z"},"links":{"cited_paper":"/paper/2501.09798","citing_paper":"/paper/2604.19657"},"observation_digest":"sha256:335378bbd0c50ffa2872f4ca03cc833158cf0b45b92ed6734780e85123280140","observation_id":"08f49dd7-b7c0-4594-b5ef-a7477a85f05f","resolution":{"observed_at":"2026-05-11T13:11:05.825940Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2501.09798/citation-record","integrity":"/paper/2501.09798/integrity","json":"/paper/2501.09798/citation-record.json","paper":"/paper/2501.09798"},"outbound":[],"paper":{"arxiv_id":"2501.09798","last_updated":"2025-05-10T02:36:13Z","latest_version":2,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-04T21:08:03.374081Z","submitted_at":"2025-01-16T19:01:25Z","title":"Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2501.09798."}