{"as_of":"2026-08-09T19:27:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4128ac9feb42d4a5b1cce158dbc2d45ee35af7d013d020da747a6565d5760753","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":"2026-08-09T06:31:02.800959+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":"2026-08-07T12:37:44.565913Z","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":"2026-05-16T11:39:22.440161Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2405.05615","last_updated":"2024-05-09T08:23:20Z","snapshot_observed_at":"2026-08-07T04:07:58.370340Z","submitted_at":"2024-05-09T08:23:20Z","title":"Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning","version":1},"cited_work":{"arxiv_id":"2405.05615","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.05615","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Memory-space visual prompting for efficient vision-language fine-tuning","venue":null,"work_id":"31253366-936f-43e4-b90b-a203fd62ffe6","year":2024},"citing_paper":{"arxiv_id":"2501.04001","last_updated":"2025-11-03T17:35:29Z","snapshot_observed_at":"2026-08-08T01:58:42.644918Z","submitted_at":"2025-01-07T18:58:54Z","title":"Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-16T11:39:22.340737Z"},"links":{"cited_paper":"/paper/2405.05615","citing_paper":"/paper/2501.04001"},"observation_digest":"sha256:9e2f90406b287f60840091fd01a3c06defb4b65d3b7eb56b589c2f11cb8115e8","observation_id":"81239117-5035-4ef5-ba23-ea0e7c5a84fe","resolution":{"observed_at":"2026-05-16T11:39:22.442369Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.05615","last_updated":"2024-05-09T08:23:20Z","snapshot_observed_at":"2026-08-07T04:07:58.370340Z","submitted_at":"2024-05-09T08:23:20Z","title":"Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.05615","snapshot_observed_at":"2026-08-07T12:37:44.565913Z","title":"Memory-space visual prompting for efficient vision-language fine-tuning.arXiv preprint arXiv:2405.05615, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.24164","last_updated":"2025-05-30T03:11:46Z","snapshot_observed_at":"2026-08-09T00:48:58.339159Z","submitted_at":"2025-05-30T03:11:46Z","title":"Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:44.565913Z"},"links":{"cited_paper":"/paper/2405.05615","citing_paper":"/paper/2505.24164"},"observation_digest":"sha256:2ff217a9baedddd87cf9dd5c20fe55848fc0c409713135a8e59d2adc6d2878a2","observation_id":"d1dc0482-7b39-4693-b682-578cc52782db","resolution":{"observed_at":"2026-08-07T12:37:44.565913Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.05615","last_updated":"2024-05-09T08:23:20Z","snapshot_observed_at":"2026-08-07T04:07:58.370340Z","submitted_at":"2024-05-09T08:23:20Z","title":"Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.05615","snapshot_observed_at":"2026-08-07T05:26:47.126961Z","title":"Memory-space visual prompting for efficient vision-language fine-tuning.arXiv preprint arXiv:2405.05615, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07971","last_updated":"2025-06-09T17:45:18Z","snapshot_observed_at":"2026-08-09T13:06:51.941159Z","submitted_at":"2025-06-09T17:45:18Z","title":"CyberV: Cybernetics for Test-time Scaling in Video Understanding","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T05:26:47.126961Z"},"links":{"cited_paper":"/paper/2405.05615","citing_paper":"/paper/2506.07971"},"observation_digest":"sha256:c09e86b79c299f53b5fd4be7d89e922b700eb61c7de988477135a3ab7bf00e3b","observation_id":"0f4d2b99-c812-4e5e-8f72-6dee08f56bee","resolution":{"observed_at":"2026-08-07T05:26:47.126961Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2405.05615/citation-record","integrity":"/paper/2405.05615/integrity","json":"/paper/2405.05615/citation-record.json","paper":"/paper/2405.05615"},"outbound":[],"paper":{"arxiv_id":"2405.05615","last_updated":"2024-05-09T08:23:20Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T04:07:58.370340Z","submitted_at":"2024-05-09T08:23:20Z","title":"Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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:2405.05615."}