{"as_of":"2026-08-12T11:51:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:df5b2787c70d2a91e1f70a2f48c0d73194f7acf4d0103189b0a0c7362252dc2e","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":"2026-08-12T06:34:41.77262+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":"2026-08-10T21:42:24.480638Z","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":"2026-05-14T01:52:01.374895Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1909.11059","last_updated":"2019-12-04T18:48:15Z","snapshot_observed_at":"2026-08-12T05:34:17.656441Z","submitted_at":"2019-09-24T17:17:26Z","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","version":3},"cited_work":{"arxiv_id":"1909.11059","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1909.11059","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Corso, and Jianfeng Gao","venue":null,"work_id":"40e2da00-5499-4283-adcf-b630daecc866","year":1909},"citing_paper":{"arxiv_id":"2308.01390","last_updated":"2023-08-07T17:53:09Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-08-02T19:10:23Z","title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-14T01:52:01.163900Z"},"links":{"cited_paper":"/paper/1909.11059","citing_paper":"/paper/2308.01390"},"observation_digest":"sha256:ebb9d7258f23e1ba0c56700658875f6f96c5c36eea981cfdfe70cc116018e9ab","observation_id":"b7f91c0e-f3c8-4297-9656-05efbaaeb3cb","resolution":{"observed_at":"2026-05-14T01:52:01.378107Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.11059","last_updated":"2019-12-04T18:48:15Z","snapshot_observed_at":"2026-08-12T05:34:17.656441Z","submitted_at":"2019-09-24T17:17:26Z","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.11059","snapshot_observed_at":"2026-08-10T21:42:24.480638Z","title":null,"venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2501.04173","last_updated":"2025-01-07T22:53:56Z","snapshot_observed_at":"2026-08-12T06:43:10.368398Z","submitted_at":"2025-01-07T22:53:56Z","title":"Multimodal Multihop Source Retrieval for Web Question Answering","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T21:42:24.480638Z"},"links":{"cited_paper":"/paper/1909.11059","citing_paper":"/paper/2501.04173"},"observation_digest":"sha256:44bc9078dcb1894a987173afc124f442a103c1ca5bf7c98f705f0602c026512a","observation_id":"180eed7a-5b7f-4fbb-bc54-b37bccbc16f7","resolution":{"observed_at":"2026-08-10T21:42:24.480638Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1909.11059","last_updated":"2019-12-04T18:48:15Z","snapshot_observed_at":"2026-08-12T05:34:17.656441Z","submitted_at":"2019-09-24T17:17:26Z","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.11059","snapshot_observed_at":"2026-08-10T20:51:53.868522Z","title":"Corso, and Jianfeng Gao","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2501.07109","last_updated":"2025-01-13T07:43:33Z","snapshot_observed_at":"2026-08-11T06:20:11.565093Z","submitted_at":"2025-01-13T07:43:33Z","title":"The Quest for Visual Understanding: A Journey Through the Evolution of Visual Question Answering","version":1},"reference_index":98,"source":"arxiv_source","source_observed_at":"2026-08-10T20:51:53.868522Z"},"links":{"cited_paper":"/paper/1909.11059","citing_paper":"/paper/2501.07109"},"observation_digest":"sha256:0e9a069488b5879cf0893a1e368096312cc3938816859056065b0f9e01e4d217","observation_id":"8029f90d-1061-4de4-a39a-82d37954b3d8","resolution":{"observed_at":"2026-08-10T20:51:53.868522Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1909.11059/citation-record","integrity":"/paper/1909.11059/integrity","json":"/paper/1909.11059/citation-record.json","paper":"/paper/1909.11059"},"outbound":[],"paper":{"arxiv_id":"1909.11059","last_updated":"2019-12-04T18:48:15Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T05:34:17.656441Z","submitted_at":"2019-09-24T17:17:26Z","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA"},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:1909.11059."}