{"as_of":"2026-08-08T13:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ca4a2999d9be9f534090149f2994678a176e34dc152845082f88713405ffeac5","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T14:27:06.572513Z","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":"2026-07-03T06:17:41.493364Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2408.13461","last_updated":"2024-08-24T04:31:37Z","snapshot_observed_at":"2026-07-06T19:05:22.642274Z","submitted_at":"2024-08-24T04:31:37Z","title":"Probing the Robustness of Vision-Language Pretrained Models: A Multimodal Adversarial Attack Approach","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.13461","snapshot_observed_at":"2026-08-07T14:27:06.572513Z","title":"Probing the robustness of vision-language pretrained models: A multimodal adversarial attack approach,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.18864","last_updated":"2025-05-24T20:46:36Z","snapshot_observed_at":"2026-08-08T00:24:14.677549Z","submitted_at":"2025-05-24T20:46:36Z","title":"Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T14:27:06.572513Z"},"links":{"cited_paper":"/paper/2408.13461","citing_paper":"/paper/2505.18864"},"observation_digest":"sha256:d72c91e35ba63ea4d1cbe4061516fbce9df08644ad548c072a3fdf6f5ed90ad8","observation_id":"647c464e-d2df-49d8-91f6-42febe3974d7","resolution":{"observed_at":"2026-08-07T14:27:06.572513Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.13461","last_updated":"2024-08-24T04:31:37Z","snapshot_observed_at":"2026-07-06T19:05:22.642274Z","submitted_at":"2024-08-24T04:31:37Z","title":"Probing the Robustness of Vision-Language Pretrained Models: A Multimodal Adversarial Attack Approach","version":1},"cited_work":{"arxiv_id":"2408.13461","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2408.13461","snapshot_observed_at":"2026-07-03T06:17:41.493364Z","title":"arXiv preprint arXiv:2408.13461 (2024)","venue":null,"work_id":"c9554828-5b23-489f-b1d7-d60c7b55f85a","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":10,"source":"pdf_text","source_observed_at":"2026-06-29T13:18:46.414179Z"},"links":{"cited_paper":"/paper/2408.13461","citing_paper":"/paper/2605.28609"},"observation_digest":"sha256:56730e8cf8c36f044395c9bdc194f0a5f69e2cca7bd9a526e7c86dda63b249f1","observation_id":"98cf7403-ed8a-4b78-8beb-113ce0daa732","resolution":{"observed_at":"2026-06-29T13:23:28.099892Z","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":"2408.13461","last_updated":"2024-08-24T04:31:37Z","snapshot_observed_at":"2026-07-06T19:05:22.642274Z","submitted_at":"2024-08-24T04:31:37Z","title":"Probing the Robustness of Vision-Language Pretrained Models: A Multimodal Adversarial Attack Approach","version":1},"cited_work":{"arxiv_id":"2408.13461","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2408.13461","snapshot_observed_at":"2026-07-03T06:17:41.493364Z","title":"arXiv preprint arXiv:2408.13461 (2024)","venue":null,"work_id":"c9554828-5b23-489f-b1d7-d60c7b55f85a","year":2024},"citing_paper":{"arxiv_id":"2606.10501","last_updated":"2026-06-09T07:26:25Z","snapshot_observed_at":"2026-08-04T16:32:33.158256Z","submitted_at":"2026-06-09T07:26:25Z","title":"Uncovering Vulnerability of Vision-Language-Action Models under Joint-Level Physical Faults","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-27T12:50:18.477396Z"},"links":{"cited_paper":"/paper/2408.13461","citing_paper":"/paper/2606.10501"},"observation_digest":"sha256:adecaca5ba1ea7357e512ab2f09173be0c968d33fe5b97151734ed76c2317767","observation_id":"01d71722-f246-4ee2-a871-fee656ec20bd","resolution":{"observed_at":"2026-07-03T06:17:41.494662Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2408.13461/citation-record","integrity":"/paper/2408.13461/integrity","json":"/paper/2408.13461/citation-record.json","paper":"/paper/2408.13461"},"outbound":[],"paper":{"arxiv_id":"2408.13461","last_updated":"2024-08-24T04:31:37Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T19:05:22.642274Z","submitted_at":"2024-08-24T04:31:37Z","title":"Probing the Robustness of Vision-Language Pretrained Models: A Multimodal Adversarial Attack Approach"},"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 3 inbound Pith citation observations for arXiv:2408.13461."}