{"as_of":"2026-08-17T22:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9dde86552a8ed9255d47c8fca976844cb20754cb632a32ba3686f2d4987450ce","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T18:09:27.073261Z","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":"2026-05-16T09:20:20.263303Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2207.07635","last_updated":"2022-07-15T17:50:51Z","snapshot_observed_at":"2026-08-17T01:12:02.486695Z","submitted_at":"2022-07-15T17:50:51Z","title":"Is a Caption Worth a Thousand Images? A Controlled Study for Representation Learning","version":1},"cited_work":{"arxiv_id":"2207.07635","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2207.07635","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2207.07635 , year=","venue":null,"work_id":"2ad02488-e830-47ca-8ce0-8191c797e3d6","year":2022},"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":31,"source":"pdf_text","source_observed_at":"2026-05-14T01:52:01.163900Z"},"links":{"cited_paper":"/paper/2207.07635","citing_paper":"/paper/2308.01390"},"observation_digest":"sha256:c7815a2c2986d1a31775e980a2513dab2adaf5433915df935a77e11386567119","observation_id":"cb7286ce-7d26-48ef-b2d2-923737e027f9","resolution":{"observed_at":"2026-05-14T01:52:01.313398Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2207.07635","last_updated":"2022-07-15T17:50:51Z","snapshot_observed_at":"2026-08-17T01:12:02.486695Z","submitted_at":"2022-07-15T17:50:51Z","title":"Is a Caption Worth a Thousand Images? A Controlled Study for Representation Learning","version":1},"cited_work":{"arxiv_id":"2207.07635","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2207.07635","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2207.07635 , year=","venue":null,"work_id":"2ad02488-e830-47ca-8ce0-8191c797e3d6","year":2022},"citing_paper":{"arxiv_id":"2309.16671","last_updated":"2025-11-23T00:34:43Z","snapshot_observed_at":"2026-08-17T12:17:37.741844Z","submitted_at":"2023-09-28T17:59:56Z","title":"Demystifying CLIP Data","version":6},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-05-16T09:20:20.143143Z"},"links":{"cited_paper":"/paper/2207.07635","citing_paper":"/paper/2309.16671"},"observation_digest":"sha256:7dc4088b766d5a5689815e1888053b1d17646c1262540132303a9fba5a0c45ec","observation_id":"3ebf95ce-3af9-4236-9b6d-85aa14afc923","resolution":{"observed_at":"2026-05-16T09:20:20.264955Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2207.07635","last_updated":"2022-07-15T17:50:51Z","snapshot_observed_at":"2026-08-17T01:12:02.486695Z","submitted_at":"2022-07-15T17:50:51Z","title":"Is a Caption Worth a Thousand Images? A Controlled Study for Representation Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.07635","snapshot_observed_at":"2026-08-12T14:08:42.119921Z","title":"Is a caption worth a thousand im- ages? a controlled study for representation learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.15628","last_updated":"2024-11-23T18:49:49Z","snapshot_observed_at":"2026-08-15T01:36:43.531267Z","submitted_at":"2024-11-23T18:49:49Z","title":"ACE: Action Concept Enhancement of Video-Language Models in Procedural Videos","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-12T14:08:42.119921Z"},"links":{"cited_paper":"/paper/2207.07635","citing_paper":"/paper/2411.15628"},"observation_digest":"sha256:fce0516bfb969655208f9bdecb2ed37e59feb04b27f080cb6f52f4be9103b6c7","observation_id":"91ad1310-2332-43cf-933a-e037b138d7c1","resolution":{"observed_at":"2026-08-12T14:08:42.119921Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2207.07635","last_updated":"2022-07-15T17:50:51Z","snapshot_observed_at":"2026-08-17T01:12:02.486695Z","submitted_at":"2022-07-15T17:50:51Z","title":"Is a Caption Worth a Thousand Images? A Controlled Study for Representation Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.07635","snapshot_observed_at":"2026-08-15T18:09:27.073261Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.18915","last_updated":"2025-07-25T03:15:16Z","snapshot_observed_at":"2026-08-16T04:40:58.556320Z","submitted_at":"2025-07-25T03:15:16Z","title":"Mining Contextualized Visual Associations from Images for Creativity Understanding","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-15T18:09:27.073261Z"},"links":{"cited_paper":"/paper/2207.07635","citing_paper":"/paper/2507.18915"},"observation_digest":"sha256:99b143e5f4a7c0b29fb85d086d6325651942fc6c2ae9b2c72b189cf0cb9866c5","observation_id":"9dd7f16e-4a0f-4bde-8ff2-cceedaa17fe7","resolution":{"observed_at":"2026-08-15T18:09:27.073261Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2207.07635/citation-record","integrity":"/paper/2207.07635/integrity","json":"/paper/2207.07635/citation-record.json","paper":"/paper/2207.07635"},"outbound":[],"paper":{"arxiv_id":"2207.07635","last_updated":"2022-07-15T17:50:51Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-17T01:12:02.486695Z","submitted_at":"2022-07-15T17:50:51Z","title":"Is a Caption Worth a Thousand Images? A Controlled Study for Representation Learning"},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2207.07635."}