{"as_of":"2026-08-07T16:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:515ef849e6f69fa1c23c4c59a87abfd15fd641242e8fcc9dab1a8e49fc871071","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":"2026-08-06T20:43:07.662405Z","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":"2504.09724","last_updated":"2025-07-01T18:36:07Z","snapshot_observed_at":"2026-08-07T16:06:05.877098Z","submitted_at":"2025-04-13T21:12:24Z","title":"A Survey on Efficient Vision-Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.09724","snapshot_observed_at":"2026-08-06T20:43:07.662405Z","title":"A survey on efficient vision-language models,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.02074","last_updated":"2025-09-08T19:23:04Z","snapshot_observed_at":"2026-08-06T20:36:27.131971Z","submitted_at":"2025-07-02T18:21:01Z","title":"Large Language Models for Crash Detection in Video: A Survey of Methods, Datasets, and Challenges","version":2},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-06T20:43:07.662405Z"},"links":{"cited_paper":"/paper/2504.09724","citing_paper":"/paper/2507.02074"},"observation_digest":"sha256:df4a892262ab5e26c068998121b88988df24041a390b3f5ac84e770862e631c4","observation_id":"c44dce93-6c64-4a7e-b261-b9159e25900e","resolution":{"observed_at":"2026-08-06T20:43:07.662405Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.09724","last_updated":"2025-07-01T18:36:07Z","snapshot_observed_at":"2026-08-07T16:06:05.877098Z","submitted_at":"2025-04-13T21:12:24Z","title":"A Survey on Efficient Vision-Language Models","version":3},"cited_work":{"arxiv_id":"2504.09724","doi":"10.48550/arxiv.2504.09724","metadata_source":"arxiv_reference","pith_arxiv_id":"2504.09724","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Gursimran Singh, Xinglu Wang, Yifan Hu, Timothy Yu, Linzi Xing, Wei Jiang, Zhefeng Wang, Xiaolong Bai, Yi Li, Ying Xiong, and 1 others","venue":"ArXiv.org","work_id":"8c2161f6-e5d8-4150-8e25-6b3ccff01bc0","year":2024},"citing_paper":{"arxiv_id":"2604.05210","last_updated":"2026-04-06T22:10:05Z","snapshot_observed_at":"2026-07-06T22:54:00.211106Z","submitted_at":"2026-04-06T22:10:05Z","title":"Integration of Object Detection and Small VLMs for Construction Safety Hazard Identification","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-05-10T19:20:29.951227Z"},"links":{"cited_paper":"/paper/2504.09724","citing_paper":"/paper/2604.05210"},"observation_digest":"sha256:8fa609121d53c9176fc85b72822e98f6dcfe01a0a855be2718afe3455cbd39cd","observation_id":"d48a61cf-82d0-496d-a8aa-2c9b0eeed8d6","resolution":{"observed_at":"2026-05-10T19:20:44.240122Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2504.09724","last_updated":"2025-07-01T18:36:07Z","snapshot_observed_at":"2026-08-07T16:06:05.877098Z","submitted_at":"2025-04-13T21:12:24Z","title":"A Survey on Efficient Vision-Language Models","version":3},"cited_work":{"arxiv_id":"2504.09724","doi":"10.48550/arxiv.2504.09724","metadata_source":"arxiv_reference","pith_arxiv_id":"2504.09724","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Gursimran Singh, Xinglu Wang, Yifan Hu, Timothy Yu, Linzi Xing, Wei Jiang, Zhefeng Wang, Xiaolong Bai, Yi Li, Ying Xiong, and 1 others","venue":"ArXiv.org","work_id":"8c2161f6-e5d8-4150-8e25-6b3ccff01bc0","year":2024},"citing_paper":{"arxiv_id":"2604.05546","last_updated":"2026-04-14T01:04:46Z","snapshot_observed_at":"2026-08-05T11:51:07.603519Z","submitted_at":"2026-04-07T07:44:11Z","title":"Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-10T18:54:04.104227Z"},"links":{"cited_paper":"/paper/2504.09724","citing_paper":"/paper/2604.05546"},"observation_digest":"sha256:0d9c97c57150e3a240acf30435bed4f0567ce9cd42e5d21e59e1dc9fa7e719be","observation_id":"ef5461d5-26e8-496c-9e91-64e94d9bf50e","resolution":{"observed_at":"2026-05-10T23:45:50.890631Z","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/2504.09724/citation-record","integrity":"/paper/2504.09724/integrity","json":"/paper/2504.09724/citation-record.json","paper":"/paper/2504.09724"},"outbound":[],"paper":{"arxiv_id":"2504.09724","last_updated":"2025-07-01T18:36:07Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T16:06:05.877098Z","submitted_at":"2025-04-13T21:12:24Z","title":"A Survey on Efficient Vision-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 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2504.09724."}