{"as_of":"2026-08-16T05:45:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:763580ebe46cf4b664f412731f9f151c8d8852925031dc92bc60572f1586b250","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":"2026-08-15T06:32:42.880941+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":"2026-08-11T16:32:24.340654Z","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":"2026-05-20T10:43:12.567797Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2203.09067","last_updated":"2022-03-17T03:53:11Z","snapshot_observed_at":"2026-08-13T16:20:55.526622Z","submitted_at":"2022-03-17T03:53:11Z","title":"UNIMO-2: End-to-End Unified Vision-Language Grounded Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.09067","snapshot_observed_at":"2026-08-11T16:32:24.340654Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.10029","last_updated":"2024-12-13T10:39:31Z","snapshot_observed_at":"2026-08-12T06:42:37.893819Z","submitted_at":"2024-12-13T10:39:31Z","title":"Enhancing Fine-Grained Vision-Language Pretraining with Negative Augmented Samples","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-11T16:32:24.340654Z"},"links":{"cited_paper":"/paper/2203.09067","citing_paper":"/paper/2412.10029"},"observation_digest":"sha256:097faa4e93ade60218f49897fcb5fab088953007325041affb8105cba342acee","observation_id":"45f6560e-3897-46a5-af50-566ea777affd","resolution":{"observed_at":"2026-08-11T16:32:24.340654Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.09067","last_updated":"2022-03-17T03:53:11Z","snapshot_observed_at":"2026-08-13T16:20:55.526622Z","submitted_at":"2022-03-17T03:53:11Z","title":"UNIMO-2: End-to-End Unified Vision-Language Grounded Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.09067","snapshot_observed_at":"2026-08-10T21:46:29.268960Z","title":"Unimo-2: End-to-end unified vision-language grounded learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.03939","last_updated":"2025-01-11T14:21:37Z","snapshot_observed_at":"2026-08-11T03:31:24.809067Z","submitted_at":"2025-01-07T17:00:35Z","title":"Visual question answering: from early developments to recent advances -- a survey","version":2},"reference_index":254,"source":"arxiv_source","source_observed_at":"2026-08-10T21:46:29.268960Z"},"links":{"cited_paper":"/paper/2203.09067","citing_paper":"/paper/2501.03939"},"observation_digest":"sha256:decb4ccde602d223ebe2a5143ef9687100e9e794d760743e28cb4f6876a1efad","observation_id":"e642db5e-37b7-4813-9d80-47e8aa636e2f","resolution":{"observed_at":"2026-08-10T21:46:29.268960Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.09067","last_updated":"2022-03-17T03:53:11Z","snapshot_observed_at":"2026-08-13T16:20:55.526622Z","submitted_at":"2022-03-17T03:53:11Z","title":"UNIMO-2: End-to-End Unified Vision-Language Grounded Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.09067","snapshot_observed_at":"2026-08-06T18:32:54.755656Z","title":"Unimo-2: End-to- end unified vision-language grounded learning.arXiv preprint arXiv:2203.09067, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.07997","last_updated":"2025-07-14T09:33:58Z","snapshot_observed_at":"2026-08-15T18:20:47.360148Z","submitted_at":"2025-07-10T17:59:54Z","title":"MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T18:32:54.755656Z"},"links":{"cited_paper":"/paper/2203.09067","citing_paper":"/paper/2507.07997"},"observation_digest":"sha256:19ef0b31adaa387cd8f9640aaf6826c60535816d8f6dd1ec7a153a0ba40edce2","observation_id":"7b2b4650-5df9-4f6d-9f0b-f383f0ea5116","resolution":{"observed_at":"2026-08-06T18:32:54.755656Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.09067","last_updated":"2022-03-17T03:53:11Z","snapshot_observed_at":"2026-08-13T16:20:55.526622Z","submitted_at":"2022-03-17T03:53:11Z","title":"UNIMO-2: End-to-End Unified Vision-Language Grounded Learning","version":1},"cited_work":{"arxiv_id":"2203.09067","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2203.09067","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"7ffe11b3-55db-403f-8bce-3eccfb30adcf","year":2022},"citing_paper":{"arxiv_id":"2605.18257","last_updated":"2026-05-18T11:56:19Z","snapshot_observed_at":"2026-07-06T23:29:09.538843Z","submitted_at":"2026-05-18T11:56:19Z","title":"CodeBind: Decoupled Representation Learning for Multimodal Alignment with Unified Compositional Codebook","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-20T10:40:56.726020Z"},"links":{"cited_paper":"/paper/2203.09067","citing_paper":"/paper/2605.18257"},"observation_digest":"sha256:dd713168848c2ca9406d9146f522dc7ccf9bdefe760e2a4b29acf8acd6279299","observation_id":"4200575c-d8cf-4f29-8547-a760be096b83","resolution":{"observed_at":"2026-05-20T10:43:12.569437Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2203.09067/citation-record","integrity":"/paper/2203.09067/integrity","json":"/paper/2203.09067/citation-record.json","paper":"/paper/2203.09067"},"outbound":[],"paper":{"arxiv_id":"2203.09067","last_updated":"2022-03-17T03:53:11Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-13T16:20:55.526622Z","submitted_at":"2022-03-17T03:53:11Z","title":"UNIMO-2: End-to-End Unified Vision-Language Grounded 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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2203.09067."}