{"as_of":"2026-08-07T05:38:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e2aa2c13e82c16bd47ac624ee4cab05a47c028c30c05eeaaa135e804bba4c0a8","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":"2026-08-06T06:34:29.942622+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":"2026-08-06T20:47:51.264678Z","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":"2026-07-03T01:27:30.973754Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2403.09572","last_updated":"2024-10-15T04:55:36Z","snapshot_observed_at":"2026-07-06T17:44:41.822709Z","submitted_at":"2024-03-14T17:03:04Z","title":"Eyes Closed, Safety On: Protecting Multimodal LLMs via Image-to-Text Transformation","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.09572","snapshot_observed_at":"2026-08-06T20:47:51.264678Z","title":"arXiv preprint arXiv:2403.09572 (2024) 1","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.01735","last_updated":"2025-07-02T14:10:25Z","snapshot_observed_at":"2026-08-06T20:41:47.142289Z","submitted_at":"2025-07-02T14:10:25Z","title":"ECCV 2024 W-CODA: 1st Workshop on Multimodal Perception and Comprehension of Corner Cases in Autonomous Driving","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T20:47:51.264678Z"},"links":{"cited_paper":"/paper/2403.09572","citing_paper":"/paper/2507.01735"},"observation_digest":"sha256:37ff30f5f413b169e0e45090edd908e8ddb5bf0c8e3f6be0f1d85533a1161812","observation_id":"1b18a055-dc06-4030-bc22-a9b9747bf208","resolution":{"observed_at":"2026-08-06T20:47:51.264678Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.09572","last_updated":"2024-10-15T04:55:36Z","snapshot_observed_at":"2026-07-06T17:44:41.822709Z","submitted_at":"2024-03-14T17:03:04Z","title":"Eyes Closed, Safety On: Protecting Multimodal LLMs via Image-to-Text Transformation","version":4},"cited_work":{"arxiv_id":"2403.09572","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.09572","snapshot_observed_at":"2026-07-03T01:27:30.973754Z","title":"Kwok, and Yu Zhang","venue":null,"work_id":"3e70f1a7-6b86-4d13-8af3-9c79dd6a6285","year":2024},"citing_paper":{"arxiv_id":"2605.01449","last_updated":"2026-05-02T13:56:50Z","snapshot_observed_at":"2026-08-03T12:34:05.607551Z","submitted_at":"2026-05-02T13:56:50Z","title":"VisInject: Disruption != Injection -- A Dual-Dimension Evaluation of Universal Adversarial Attacks on Vision-Language Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-09T14:24:48.999632Z"},"links":{"cited_paper":"/paper/2403.09572","citing_paper":"/paper/2605.01449"},"observation_digest":"sha256:e82679d012aa5fd0429751cf21431d4c73a18ba1df60badf6370d6d11864fb3d","observation_id":"63ef78a9-faad-41e7-b098-48561192df80","resolution":{"observed_at":"2026-05-11T16:56:08.027696Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.09572","last_updated":"2024-10-15T04:55:36Z","snapshot_observed_at":"2026-07-06T17:44:41.822709Z","submitted_at":"2024-03-14T17:03:04Z","title":"Eyes Closed, Safety On: Protecting Multimodal LLMs via Image-to-Text Transformation","version":4},"cited_work":{"arxiv_id":"2403.09572","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.09572","snapshot_observed_at":"2026-07-03T01:27:30.973754Z","title":"Kwok, and Yu Zhang","venue":null,"work_id":"3e70f1a7-6b86-4d13-8af3-9c79dd6a6285","year":2024},"citing_paper":{"arxiv_id":"2606.09125","last_updated":"2026-06-08T07:19:42Z","snapshot_observed_at":"2026-07-06T23:48:30.569726Z","submitted_at":"2026-06-08T07:19:42Z","title":"Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges","version":1},"reference_index":87,"source":"arxiv_source","source_observed_at":"2026-06-27T16:33:28.848573Z"},"links":{"cited_paper":"/paper/2403.09572","citing_paper":"/paper/2606.09125"},"observation_digest":"sha256:11dc524e578840eddc36ce2442b535ceddb8ade8d66bfa8d513173c98b1a8440","observation_id":"279ec03b-0a0f-4d8e-acbd-334326207cbd","resolution":{"observed_at":"2026-07-03T01:27:30.975148Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2403.09572/citation-record","integrity":"/paper/2403.09572/integrity","json":"/paper/2403.09572/citation-record.json","paper":"/paper/2403.09572"},"outbound":[],"paper":{"arxiv_id":"2403.09572","last_updated":"2024-10-15T04:55:36Z","latest_version":4,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T17:44:41.822709Z","submitted_at":"2024-03-14T17:03:04Z","title":"Eyes Closed, Safety On: Protecting Multimodal LLMs via Image-to-Text Transformation"},"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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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:2403.09572."}