{"as_of":"2026-08-09T03:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:928a4337a3344930d79bb7d367153f75ab3d18525966d0495b8d5456eb144cd9","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":"2026-08-07T13:45:53.573721Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-05T18:00:43.120575Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2312.00784","last_updated":"2024-04-27T01:53:39Z","snapshot_observed_at":"2026-08-09T03:33:29.453781Z","submitted_at":"2023-12-01T18:59:56Z","title":"ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.00784","snapshot_observed_at":"2026-08-07T13:45:53.573721Z","title":"Meyer, Yuning Chai, and Yong Jae Lee","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21061","last_updated":"2025-05-27T11:47:28Z","snapshot_observed_at":"2026-08-08T23:47:58.987947Z","submitted_at":"2025-05-27T11:47:28Z","title":"LPOI: Listwise Preference Optimization for Vision Language Models","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-07T13:45:53.573721Z"},"links":{"cited_paper":"/paper/2312.00784","citing_paper":"/paper/2505.21061"},"observation_digest":"sha256:b5da8330edc65dec17bf943ed3a8fc3d0ac75897d69a8589952f2e1ac466955a","observation_id":"cf14ef7f-11e3-4a74-9ed1-e4f5ea5cb9e4","resolution":{"observed_at":"2026-08-07T13:45:53.573721Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.00784","last_updated":"2024-04-27T01:53:39Z","snapshot_observed_at":"2026-08-09T03:33:29.453781Z","submitted_at":"2023-12-01T18:59:56Z","title":"ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.00784","snapshot_observed_at":"2026-08-07T00:31:32.709825Z","title":"arXiv preprint arXiv:2312.00784","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.13901","last_updated":"2025-06-16T18:22:28Z","snapshot_observed_at":"2026-08-09T03:33:57.239039Z","submitted_at":"2025-06-16T18:22:28Z","title":"Alignment Quality Index (AQI) : Beyond Refusals: AQI as an Intrinsic Alignment Diagnostic via Latent Geometry, Cluster Divergence, and Layer wise Pooled Representations","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-07T00:31:32.709825Z"},"links":{"cited_paper":"/paper/2312.00784","citing_paper":"/paper/2506.13901"},"observation_digest":"sha256:eed3a40c8e2f4cd70bb330250b32c740fc994d71474f2cb58eff6790e055744f","observation_id":"f2508823-1c46-4071-bbf4-ea4e41a2ca42","resolution":{"observed_at":"2026-08-07T00:31:32.709825Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.00784","last_updated":"2024-04-27T01:53:39Z","snapshot_observed_at":"2026-08-09T03:33:29.453781Z","submitted_at":"2023-12-01T18:59:56Z","title":"ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts","version":2},"cited_work":{"arxiv_id":"2312.00784","doi":null,"metadata_source":"pith","pith_arxiv_id":"2312.00784","snapshot_observed_at":"2026-08-05T18:00:43.120575Z","title":"ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts","venue":"cs.CV","work_id":"b482d2c4-2155-4a11-b1c3-db5fd10daf27","year":2023},"citing_paper":{"arxiv_id":"2508.15297","last_updated":"2025-08-21T06:36:24Z","snapshot_observed_at":"2026-08-09T03:33:00.944417Z","submitted_at":"2025-08-21T06:36:24Z","title":"DesignCLIP: Multimodal Learning with CLIP for Design Patent Understanding","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T18:00:33.177933Z"},"links":{"cited_paper":"/paper/2312.00784","citing_paper":"/paper/2508.15297"},"observation_digest":"sha256:75a7e2d5c5343437ce9674e21c43f925d0ccbe0e447f9768335f0bc6f7868e11","observation_id":"f98d3dc1-595c-4b73-a7b4-724dd6aabe57","resolution":{"observed_at":"2026-08-05T18:00:43.188358Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"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/2312.00784/citation-record","integrity":"/paper/2312.00784/integrity","json":"/paper/2312.00784/citation-record.json","paper":"/paper/2312.00784"},"outbound":[],"paper":{"arxiv_id":"2312.00784","last_updated":"2024-04-27T01:53:39Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T03:33:29.453781Z","submitted_at":"2023-12-01T18:59:56Z","title":"ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts"},"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 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2312.00784."}