{"as_of":"2026-08-07T15:32:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9dce655d42758d7b4274e6674e7f2aa27922bcdce26dfc54aabc2968de37969b","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":1,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":1,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-20T06:20:36.235304Z","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":"2026-05-20T06:20:36.493001Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2305.14800","last_updated":"2024-01-23T04:01:43Z","snapshot_observed_at":"2026-07-06T15:32:18.583350Z","submitted_at":"2023-05-24T06:52:47Z","title":"Exploring Diverse In-Context Configurations for Image Captioning","version":6},"cited_work":{"arxiv_id":"2305.14800","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2305.14800","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2305.14800 , year=","venue":null,"work_id":"8034a3f2-0f93-495d-869e-7e834f3efddf","year":null},"citing_paper":{"arxiv_id":"2408.04840","last_updated":"2024-08-13T08:10:32Z","snapshot_observed_at":"2026-07-06T18:58:39.334273Z","submitted_at":"2024-08-09T03:25:42Z","title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","version":2},"reference_index":112,"source":"arxiv_source","source_observed_at":"2026-05-20T06:20:36.235304Z"},"links":{"cited_paper":"/paper/2305.14800","citing_paper":"/paper/2408.04840"},"observation_digest":"sha256:b95c837b5a9022364c54795c6cf0c374db3cfe605d37703cd2cfdde6c6034579","observation_id":"a3829c38-823c-4691-beb7-0f3f0998ebda","resolution":{"observed_at":"2026-05-20T06:20:36.495065Z","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/2305.14800/citation-record","integrity":"/paper/2305.14800/integrity","json":"/paper/2305.14800/citation-record.json","paper":"/paper/2305.14800"},"outbound":[],"paper":{"arxiv_id":"2305.14800","last_updated":"2024-01-23T04:01:43Z","latest_version":6,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T15:32:18.583350Z","submitted_at":"2023-05-24T06:52:47Z","title":"Exploring Diverse In-Context Configurations for Image Captioning"},"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 1 inbound Pith citation observation for arXiv:2305.14800."}