{"as_of":"2026-08-06T23:55:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:15fef1a9a4535607e00ff5cf29768787ffdf7d40d100cb38658889002b546f41","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":"2026-06-29T13:18:46.414179Z","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":"2026-07-03T04:37:37.265347Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2403.10883","last_updated":"2024-07-08T12:03:14Z","snapshot_observed_at":"2026-08-06T17:24:14.363771Z","submitted_at":"2024-03-16T10:32:24Z","title":"Improving Adversarial Transferability of Vision-Language Pre-training Models through Collaborative Multimodal Interaction","version":2},"cited_work":{"arxiv_id":"2403.10883","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.10883","snapshot_observed_at":"2026-07-03T04:37:37.265347Z","title":"Improving adversarial transferability of vision-language pre-training models through collaborative multimodal interaction,","venue":null,"work_id":"3b61e445-d09d-4c97-8533-538b0afc8b5f","year":2024},"citing_paper":{"arxiv_id":"2605.28083","last_updated":"2026-05-27T07:38:16Z","snapshot_observed_at":"2026-07-06T23:37:40.695655Z","submitted_at":"2026-05-27T07:38:16Z","title":"VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-29T12:59:17.093731Z"},"links":{"cited_paper":"/paper/2403.10883","citing_paper":"/paper/2605.28083"},"observation_digest":"sha256:80cec3542b2a955785981f1376482b185bbef6ec8340a69aaf1466d9d6e6e7bb","observation_id":"a9f6b117-8132-47f9-bb30-3b16c7d3caf4","resolution":{"observed_at":"2026-06-29T13:03:26.170383Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2403.10883","last_updated":"2024-07-08T12:03:14Z","snapshot_observed_at":"2026-08-06T17:24:14.363771Z","submitted_at":"2024-03-16T10:32:24Z","title":"Improving Adversarial Transferability of Vision-Language Pre-training Models through Collaborative Multimodal Interaction","version":2},"cited_work":{"arxiv_id":"2403.10883","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.10883","snapshot_observed_at":"2026-07-03T04:37:37.265347Z","title":"Improving adversarial transferability of vision-language pre-training models through collaborative multimodal interaction,","venue":null,"work_id":"3b61e445-d09d-4c97-8533-538b0afc8b5f","year":2024},"citing_paper":{"arxiv_id":"2605.28609","last_updated":"2026-05-27T15:24:31Z","snapshot_observed_at":"2026-08-03T19:09:23.628613Z","submitted_at":"2026-05-27T15:24:31Z","title":"JECA^2: Judgment-Explanation Consistent Adversarial Attack against Forensic Vision-Language Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-29T13:18:46.414179Z"},"links":{"cited_paper":"/paper/2403.10883","citing_paper":"/paper/2605.28609"},"observation_digest":"sha256:4c82aeccb65eeee5898a6d645d0a3e28e27f104c7f39e3c763726370f2defe5f","observation_id":"a945c67f-06a7-425b-9a81-4c7d7312538e","resolution":{"observed_at":"2026-06-29T13:23:28.106598Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2403.10883","last_updated":"2024-07-08T12:03:14Z","snapshot_observed_at":"2026-08-06T17:24:14.363771Z","submitted_at":"2024-03-16T10:32:24Z","title":"Improving Adversarial Transferability of Vision-Language Pre-training Models through Collaborative Multimodal Interaction","version":2},"cited_work":{"arxiv_id":"2403.10883","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.10883","snapshot_observed_at":"2026-07-03T04:37:37.265347Z","title":"Improving adversarial transferability of vision-language pre-training models through collaborative multimodal interaction,","venue":null,"work_id":"3b61e445-d09d-4c97-8533-538b0afc8b5f","year":2024},"citing_paper":{"arxiv_id":"2606.10571","last_updated":"2026-06-09T08:34:01Z","snapshot_observed_at":"2026-08-02T23:16:13.992416Z","submitted_at":"2026-06-09T08:34:01Z","title":"Improving Adversarial Transferability on Vision-Language Pre-training Models via Surrogate-Specific Bias Correction","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-06-27T13:46:06.519188Z"},"links":{"cited_paper":"/paper/2403.10883","citing_paper":"/paper/2606.10571"},"observation_digest":"sha256:becc2f32f8cc7de27a47c302eed3fe27a2f3d88a33256f07f377517a35d0e55e","observation_id":"2e635225-c99f-4364-9e2b-53f27ae527e1","resolution":{"observed_at":"2026-07-03T04:37:37.266861Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2403.10883/citation-record","integrity":"/paper/2403.10883/integrity","json":"/paper/2403.10883/citation-record.json","paper":"/paper/2403.10883"},"outbound":[],"paper":{"arxiv_id":"2403.10883","last_updated":"2024-07-08T12:03:14Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T17:24:14.363771Z","submitted_at":"2024-03-16T10:32:24Z","title":"Improving Adversarial Transferability of Vision-Language Pre-training Models through Collaborative Multimodal Interaction"},"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 6 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2403.10883."}