{"as_of":"2026-08-09T01:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:67275ca256de7fe2fa318ed507bb157b59c00f8f3fc3f70695c73ea18d877022","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":"2026-08-07T13:09:55.512739Z","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":"2026-05-13T17:08:12.927865Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2307.10350","last_updated":"2023-10-26T03:41:06Z","snapshot_observed_at":"2026-07-06T15:56:07.787414Z","submitted_at":"2023-07-19T17:47:12Z","title":"Improving Multimodal Datasets with Image Captioning","version":2},"cited_work":{"arxiv_id":"2307.10350","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2307.10350","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Improving multi- modal datasets with image captioning","venue":null,"work_id":"7699e9ea-6ee9-4472-abbc-c90e62e85b9e","year":2023},"citing_paper":{"arxiv_id":"2311.12793","last_updated":"2023-11-28T08:52:50Z","snapshot_observed_at":"2026-08-04T08:17:54.774738Z","submitted_at":"2023-11-21T18:58:11Z","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-13T17:08:12.727773Z"},"links":{"cited_paper":"/paper/2307.10350","citing_paper":"/paper/2311.12793"},"observation_digest":"sha256:c45366c29df06f790bbe80f8e66deac880394d62904e120d093bca18d11fdf0a","observation_id":"41cd977a-32e4-4b8f-b1a5-1a4f37b954ef","resolution":{"observed_at":"2026-05-13T17:08:12.931839Z","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":"2307.10350","last_updated":"2023-10-26T03:41:06Z","snapshot_observed_at":"2026-07-06T15:56:07.787414Z","submitted_at":"2023-07-19T17:47:12Z","title":"Improving Multimodal Datasets with Image Captioning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.10350","snapshot_observed_at":"2026-08-07T13:09:55.512739Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.22627","last_updated":"2025-06-01T02:55:39Z","snapshot_observed_at":"2026-08-08T13:58:01.163947Z","submitted_at":"2025-05-28T17:45:55Z","title":"Chain-of-Talkers (CoTalk): Fast Human Annotation of Dense Image Captions","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-07T13:09:55.512739Z"},"links":{"cited_paper":"/paper/2307.10350","citing_paper":"/paper/2505.22627"},"observation_digest":"sha256:637c1adc67ce3890dae4c07adadc804e05ddd96fced4a524c923d99fa8b1934b","observation_id":"746f77a6-0a68-42e1-a895-63cc1e808e60","resolution":{"observed_at":"2026-08-07T13:09:55.512739Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.10350","last_updated":"2023-10-26T03:41:06Z","snapshot_observed_at":"2026-07-06T15:56:07.787414Z","submitted_at":"2023-07-19T17:47:12Z","title":"Improving Multimodal Datasets with Image Captioning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.10350","snapshot_observed_at":"2026-08-05T14:59:19.587481Z","title":"Improving multimodal datasets with image captioning.arXiv preprint arXiv:2307.10350 ,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.20691","last_updated":"2025-08-28T11:50:22Z","snapshot_observed_at":"2026-08-06T13:33:55.665527Z","submitted_at":"2025-08-28T11:50:22Z","title":"MobileCLIP2: Improving Multi-Modal Reinforced Training","version":1},"reference_index":2012,"source":"pdf_text","source_observed_at":"2026-08-05T14:59:19.587481Z"},"links":{"cited_paper":"/paper/2307.10350","citing_paper":"/paper/2508.20691"},"observation_digest":"sha256:b8a1faeed4089c038f8d007ea07cce7614c8c92279d4cc464d350c671fa75dd2","observation_id":"90cb5605-90a4-4b77-8fab-9e3e7a22ccbf","resolution":{"observed_at":"2026-08-05T14:59:19.587481Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2307.10350/citation-record","integrity":"/paper/2307.10350/integrity","json":"/paper/2307.10350/citation-record.json","paper":"/paper/2307.10350"},"outbound":[],"paper":{"arxiv_id":"2307.10350","last_updated":"2023-10-26T03:41:06Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T15:56:07.787414Z","submitted_at":"2023-07-19T17:47:12Z","title":"Improving Multimodal Datasets with 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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2307.10350."}