{"as_of":"2026-08-08T23:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0ab7f4403c1ddf7644b831319925764fb331ee9e1537e5a1dc90e0e5a2e37964","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":"2026-08-08T06:32:00.761636+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":"2026-08-06T05:51:15.918167Z","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":"2026-05-16T20:54:07.622646Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2111.12727","last_updated":"2023-11-30T11:47:36Z","snapshot_observed_at":"2026-08-04T15:32:23.202100Z","submitted_at":"2021-11-24T19:00:05Z","title":"Generating More Pertinent Captions by Leveraging Semantics and Style on Multi-Source Datasets","version":3},"cited_work":{"arxiv_id":"2111.12727","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2111.12727","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Universal captioner: Long-tail vision-and-language model training through content-style separation.arXiv preprint arXiv:2111.12727","venue":null,"work_id":"8147134b-8245-480c-a294-d5382f4aa9aa","year":null},"citing_paper":{"arxiv_id":"2205.14100","last_updated":"2022-12-15T19:21:35Z","snapshot_observed_at":"2026-08-04T09:31:34.784365Z","submitted_at":"2022-05-27T17:03:38Z","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","version":5},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-16T20:54:07.572136Z"},"links":{"cited_paper":"/paper/2111.12727","citing_paper":"/paper/2205.14100"},"observation_digest":"sha256:73e11c399bd922c5933bc7caf65d7cd10ea2156fa0b2a5bfa1714a980bffa43f","observation_id":"1c6f4223-f62f-46a5-b315-f09142c86efe","resolution":{"observed_at":"2026-05-16T20:54:07.624686Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2111.12727","last_updated":"2023-11-30T11:47:36Z","snapshot_observed_at":"2026-08-04T15:32:23.202100Z","submitted_at":"2021-11-24T19:00:05Z","title":"Generating More Pertinent Captions by Leveraging Semantics and Style on Multi-Source Datasets","version":3},"cited_work":{"arxiv_id":"2111.12727","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2111.12727","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Universal captioner: Long-tail vision-and-language model training through content-style separation.arXiv preprint arXiv:2111.12727","venue":null,"work_id":"8147134b-8245-480c-a294-d5382f4aa9aa","year":null},"citing_paper":{"arxiv_id":"2311.03079","last_updated":"2024-02-04T08:23:04Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-11-06T13:04:39Z","title":"CogVLM: Visual Expert for Pretrained Language Models","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-15T15:46:06.334088Z"},"links":{"cited_paper":"/paper/2111.12727","citing_paper":"/paper/2311.03079"},"observation_digest":"sha256:5f919987c57294e4e33c2e0d001ab8970b6aa9600e30cf5db3d21df505d08f78","observation_id":"09cd8215-1680-48de-993a-e4103b1646ff","resolution":{"observed_at":"2026-05-15T15:46:06.472683Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2111.12727","last_updated":"2023-11-30T11:47:36Z","snapshot_observed_at":"2026-08-04T15:32:23.202100Z","submitted_at":"2021-11-24T19:00:05Z","title":"Generating More Pertinent Captions by Leveraging Semantics and Style on Multi-Source Datasets","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.12727","snapshot_observed_at":"2026-08-06T05:51:15.918167Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.01236","last_updated":"2025-08-02T07:22:08Z","snapshot_observed_at":"2026-08-07T10:22:34.344208Z","submitted_at":"2025-08-02T07:22:08Z","title":"Mitigating Information Loss under High Pruning Rates for Efficient Large Vision Language Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T05:51:15.918167Z"},"links":{"cited_paper":"/paper/2111.12727","citing_paper":"/paper/2508.01236"},"observation_digest":"sha256:7dd42d4acf5c4406f9751d060b2ee4a7632bc95557fd1e66b1ffe227ae103304","observation_id":"36ba18d9-dc18-4cb0-b269-95216a259cdd","resolution":{"observed_at":"2026-08-06T05:51:15.918167Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2111.12727/citation-record","integrity":"/paper/2111.12727/integrity","json":"/paper/2111.12727/citation-record.json","paper":"/paper/2111.12727"},"outbound":[],"paper":{"arxiv_id":"2111.12727","last_updated":"2023-11-30T11:47:36Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-04T15:32:23.202100Z","submitted_at":"2021-11-24T19:00:05Z","title":"Generating More Pertinent Captions by Leveraging Semantics and Style on Multi-Source Datasets"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2111.12727."}