{"as_of":"2026-08-09T10:47:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a5bdcd473a16d61f3d8c5043f5f3fd399b2ff48ad82dc5d010edcca3db9e8571","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T06:00:27.375861Z","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":14,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2102.10407","last_updated":"2022-03-30T06:27:02Z","snapshot_observed_at":"2026-08-08T23:59:41.812457Z","submitted_at":"2021-02-20T18:02:42Z","title":"VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning","version":5},"cited_work":{"arxiv_id":"2102.10407","doi":"10.48550/arxiv.2102.10407","metadata_source":"arxiv_reference","pith_arxiv_id":"2102.10407","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"doi:10.48550/arXiv.2102.10407 , urldate =","venue":"arXiv (Cornell University)","work_id":"f8681480-b01e-4906-b684-05eddefe92a4","year":null},"citing_paper":{"arxiv_id":"2308.08089","last_updated":"2023-08-16T01:43:41Z","snapshot_observed_at":"2026-07-06T16:06:38.424057Z","submitted_at":"2023-08-16T01:43:41Z","title":"DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory","version":1},"reference_index":147,"source":"arxiv_source","source_observed_at":"2026-05-20T13:03:57.828598Z"},"links":{"cited_paper":"/paper/2102.10407","citing_paper":"/paper/2308.08089"},"observation_digest":"sha256:fa421fbc27fdfda552eb2577b921b0552a4e0eb7f9e49b0a0d3d8df2b385f9f0","observation_id":"a5c6a96c-a90c-4304-bd62-da4dd85500bc","resolution":{"observed_at":"2026-05-20T13:03:58.019440Z","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":"2102.10407","last_updated":"2022-03-30T06:27:02Z","snapshot_observed_at":"2026-08-08T23:59:41.812457Z","submitted_at":"2021-02-20T18:02:42Z","title":"VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.10407","snapshot_observed_at":"2026-08-05T06:00:27.375861Z","title":"VisualGPT: Data-efficient Image Captioning by Balancing Visual Input and Linguistic Knowledge from Pretraining.CoRR, abs/2102.10407, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.04606","last_updated":"2025-09-04T18:41:59Z","snapshot_observed_at":"2026-08-08T23:16:34.034930Z","submitted_at":"2025-09-04T18:41:59Z","title":"Sample-efficient Integration of New Modalities into Large Language Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T06:00:27.375861Z"},"links":{"cited_paper":"/paper/2102.10407","citing_paper":"/paper/2509.04606"},"observation_digest":"sha256:d4b568bc4adc630b483040980a72f2baad82f2c924e48abebae55b695b0f4c6c","observation_id":"fe851190-7f20-4bbe-8c17-a8977c1193f0","resolution":{"observed_at":"2026-08-05T06:00:27.375861Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2102.10407/citation-record","integrity":"/paper/2102.10407/integrity","json":"/paper/2102.10407/citation-record.json","paper":"/paper/2102.10407"},"outbound":[],"paper":{"arxiv_id":"2102.10407","last_updated":"2022-03-30T06:27:02Z","latest_version":5,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-08T23:59:41.812457Z","submitted_at":"2021-02-20T18:02:42Z","title":"VisualGPT: Data-efficient Adaptation of Pretrained Language Models 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":"2026-08-09T06:31:02.800959+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 2 inbound Pith citation observations for arXiv:2102.10407."}