{"as_of":"2026-08-07T16:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f4d7dd0976347bfe72b65515e5302a5e866a08fb0cebbb261ebe9751ed5ad908","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":"2026-08-06T17:22:14.824478Z","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":"2026-05-17T10:46:28.836878Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2305.18279","last_updated":"2024-08-12T07:14:00Z","snapshot_observed_at":"2026-08-06T08:08:30.426894Z","submitted_at":"2023-05-29T17:50:33Z","title":"Contextual Object Detection with Multimodal Large Language Models","version":2},"cited_work":{"arxiv_id":"2305.18279","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2305.18279","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Contextual object detection with multimodal large language models","venue":null,"work_id":"5d76f8a6-73d8-4fde-aa23-6b8e7c1b6993","year":2023},"citing_paper":{"arxiv_id":"2401.16420","last_updated":"2024-01-29T18:59:02Z","snapshot_observed_at":"2026-08-05T03:42:54.599829Z","submitted_at":"2024-01-29T18:59:02Z","title":"InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-05-17T05:30:27.667126Z"},"links":{"cited_paper":"/paper/2305.18279","citing_paper":"/paper/2401.16420"},"observation_digest":"sha256:7eb61296289dd403a10c9d9d3d5ffbe6433d1196c4f0b29507b4db432c268b8f","observation_id":"c5ae13a0-ca0b-4552-b3b2-894a8e259f1c","resolution":{"observed_at":"2026-05-17T05:30:27.781247Z","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":"2305.18279","last_updated":"2024-08-12T07:14:00Z","snapshot_observed_at":"2026-08-06T08:08:30.426894Z","submitted_at":"2023-05-29T17:50:33Z","title":"Contextual Object Detection with Multimodal Large Language Models","version":2},"cited_work":{"arxiv_id":"2305.18279","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2305.18279","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Contextual object detection with multimodal large language models","venue":null,"work_id":"5d76f8a6-73d8-4fde-aa23-6b8e7c1b6993","year":2023},"citing_paper":{"arxiv_id":"2407.03320","last_updated":"2024-07-03T17:59:21Z","snapshot_observed_at":"2026-08-04T22:09:42.241578Z","submitted_at":"2024-07-03T17:59:21Z","title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","version":1},"reference_index":168,"source":"pdf_text","source_observed_at":"2026-05-17T10:46:28.447347Z"},"links":{"cited_paper":"/paper/2305.18279","citing_paper":"/paper/2407.03320"},"observation_digest":"sha256:dac1ea8d64f70666895b4848f74822ce0cc1c5f4bce157d0429a207b47cd0430","observation_id":"6225230e-a9e5-42ce-be43-68b7b1b08545","resolution":{"observed_at":"2026-05-17T10:46:28.839562Z","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":"2305.18279","last_updated":"2024-08-12T07:14:00Z","snapshot_observed_at":"2026-08-06T08:08:30.426894Z","submitted_at":"2023-05-29T17:50:33Z","title":"Contextual Object Detection with Multimodal Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.18279","snapshot_observed_at":"2026-08-06T17:22:14.824478Z","title":"Contextual object detection with multimodal large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.11102","last_updated":"2025-07-15T08:52:28Z","snapshot_observed_at":"2026-08-06T17:14:03.669426Z","submitted_at":"2025-07-15T08:52:28Z","title":"KptLLM++: Towards Generic Keypoint Comprehension with Large Language Model","version":1},"reference_index":93,"source":"arxiv_source","source_observed_at":"2026-08-06T17:22:14.824478Z"},"links":{"cited_paper":"/paper/2305.18279","citing_paper":"/paper/2507.11102"},"observation_digest":"sha256:cc08c9a2957bd00f4a369c8d7f7aa0d9ae036e67248dcc31ecb11788ba210562","observation_id":"23390d0a-6e3d-4aa9-8eb2-366838c9140e","resolution":{"observed_at":"2026-08-06T17:22:14.824478Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2305.18279/citation-record","integrity":"/paper/2305.18279/integrity","json":"/paper/2305.18279/citation-record.json","paper":"/paper/2305.18279"},"outbound":[],"paper":{"arxiv_id":"2305.18279","last_updated":"2024-08-12T07:14:00Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T08:08:30.426894Z","submitted_at":"2023-05-29T17:50:33Z","title":"Contextual Object Detection with 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 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2305.18279."}