{"as_of":"2026-08-08T04:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:63f30fa82342d2d59f47bd484b181d7a1773bcd492c7ea1949232accfb7121f2","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":"2026-08-07T15:03:37.532536Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":0,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.16555","last_updated":"2025-05-29T14:05:50Z","snapshot_observed_at":"2026-07-06T20:11:24.538172Z","submitted_at":"2024-12-21T09:43:51Z","title":"Divide and Conquer: A Hybrid Strategy Defeats Multimodal Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.16555","snapshot_observed_at":"2026-08-07T15:03:37.532536Z","title":"Divide and conquer: A hybrid strategy defeats multimodal large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.16446","last_updated":"2025-05-22T09:34:47Z","snapshot_observed_at":"2026-08-08T01:24:44.977675Z","submitted_at":"2025-05-22T09:34:47Z","title":"Implicit Jailbreak Attacks via Cross-Modal Information Concealment on Vision-Language Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T15:03:37.532536Z"},"links":{"cited_paper":"/paper/2412.16555","citing_paper":"/paper/2505.16446"},"observation_digest":"sha256:29482c8e0328ece40976dd853cb322e82c956af8e81e967616860bd7205f976c","observation_id":"d1e98e82-0b23-4a76-a387-c9303797322c","resolution":{"observed_at":"2026-08-07T15:03:37.532536Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.16555","last_updated":"2025-05-29T14:05:50Z","snapshot_observed_at":"2026-07-06T20:11:24.538172Z","submitted_at":"2024-12-21T09:43:51Z","title":"Divide and Conquer: A Hybrid Strategy Defeats Multimodal Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.16555","snapshot_observed_at":"2026-08-07T04:08:49.204476Z","title":"arXiv preprint arXiv:2412.16555 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.11521","last_updated":"2025-06-13T07:22:36Z","snapshot_observed_at":"2026-08-07T12:06:46.005829Z","submitted_at":"2025-06-13T07:22:36Z","title":"Investigating Vulnerabilities and Defenses Against Audio-Visual Attacks: A Comprehensive Survey Emphasizing Multimodal Models","version":1},"reference_index":81,"source":"arxiv_source","source_observed_at":"2026-08-07T04:08:49.204476Z"},"links":{"cited_paper":"/paper/2412.16555","citing_paper":"/paper/2506.11521"},"observation_digest":"sha256:48714b6c98e54fce293350be5da6d533f84a3de8cec796ce8748c11e65e2ab10","observation_id":"41853fe8-0627-4958-8205-c12fbd969cf4","resolution":{"observed_at":"2026-08-07T04:08:49.204476Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.16555","last_updated":"2025-05-29T14:05:50Z","snapshot_observed_at":"2026-07-06T20:11:24.538172Z","submitted_at":"2024-12-21T09:43:51Z","title":"Divide and Conquer: A Hybrid Strategy Defeats Multimodal Large Language Models","version":3},"cited_work":{"arxiv_id":"2412.16555","doi":"10.48550/arxiv.2412.16555","metadata_source":"arxiv_reference","pith_arxiv_id":"2412.16555","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Divide and","venue":"arXiv (Cornell University)","work_id":"af81285f-1cd6-4c94-9d7d-21c88512fb37","year":null},"citing_paper":{"arxiv_id":"2606.06840","last_updated":"2026-06-05T02:32:24Z","snapshot_observed_at":"2026-08-05T15:03:33.373071Z","submitted_at":"2026-06-05T02:32:24Z","title":"Characterize Then Distill: Mechanistic Reasoning in Large Output Spaces","version":1},"reference_index":144,"source":"arxiv_source","source_observed_at":"2026-06-27T22:22:52.690010Z"},"links":{"cited_paper":"/paper/2412.16555","citing_paper":"/paper/2606.06840"},"observation_digest":"sha256:f4faf61da8dc77ee3e99fbf844583dd11e37271e82f1e1dd623f2b652b3a07c2","observation_id":"0dca4246-f6e8-4647-8161-e6b45f83d222","resolution":{"observed_at":"2026-06-27T22:31:21.590883Z","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/2412.16555/citation-record","integrity":"/paper/2412.16555/integrity","json":"/paper/2412.16555/citation-record.json","paper":"/paper/2412.16555"},"outbound":[],"paper":{"arxiv_id":"2412.16555","last_updated":"2025-05-29T14:05:50Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T20:11:24.538172Z","submitted_at":"2024-12-21T09:43:51Z","title":"Divide and Conquer: A Hybrid Strategy Defeats Multimodal Large Language 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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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:2412.16555."}