{"as_of":"2026-08-05T20:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e1bba9d04d27fed817708b0fca4cc2425cc1f69d3447de5b73a04db88b8904f3","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-05T06:32:48.257954+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-31T06:20:13.947108Z","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":"2026-05-13T22:46:10.185714Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2205.03860","last_updated":"2023-11-08T09:45:00Z","snapshot_observed_at":"2026-07-06T13:07:48.490715Z","submitted_at":"2022-05-08T13:19:23Z","title":"CCMB: A Large-scale Chinese Cross-modal Benchmark","version":6},"cited_work":{"arxiv_id":"2205.03860","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2205.03860","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Zero and r2d2: A large-scale chi- nese cross-modal benchmark and a vision-language frame- work","venue":null,"work_id":"aa6eae88-d2b4-4235-a8ed-7c78287c0e27","year":2022},"citing_paper":{"arxiv_id":"2312.14238","last_updated":"2024-01-15T15:23:55Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-21T18:59:31Z","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","version":3},"reference_index":160,"source":"pdf_text","source_observed_at":"2026-05-13T22:46:09.693156Z"},"links":{"cited_paper":"/paper/2205.03860","citing_paper":"/paper/2312.14238"},"observation_digest":"sha256:b909d2eef67291e279098acb2cf5e80a260f314fdaf9fac30e47dbfc6e00aea5","observation_id":"bf5210bf-3229-4c94-9a2b-1702d77bea37","resolution":{"observed_at":"2026-05-13T22:46:10.188399Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.03860","last_updated":"2023-11-08T09:45:00Z","snapshot_observed_at":"2026-07-06T13:07:48.490715Z","submitted_at":"2022-05-08T13:19:23Z","title":"CCMB: A Large-scale Chinese Cross-modal Benchmark","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.03860","snapshot_observed_at":"2026-07-31T06:20:13.947108Z","title":"CCMB: A large-scale chinese cross-modal benchmark","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24904","last_updated":"2026-07-27T17:59:53Z","snapshot_observed_at":"2026-08-01T00:03:26.264908Z","submitted_at":"2026-07-27T17:59:53Z","title":"Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-07-31T06:20:13.947108Z"},"links":{"cited_paper":"/paper/2205.03860","citing_paper":"/paper/2607.24904"},"observation_digest":"sha256:051b62b04647b97bb149eb68e409c90b9781d6e1c6b3db1e5fc2e7527caeb4e4","observation_id":"55899e84-5c30-4128-b356-fb67e57ba6f0","resolution":{"observed_at":"2026-07-31T06:20:13.947108Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2205.03860/citation-record","integrity":"/paper/2205.03860/integrity","json":"/paper/2205.03860/citation-record.json","paper":"/paper/2205.03860"},"outbound":[],"paper":{"arxiv_id":"2205.03860","last_updated":"2023-11-08T09:45:00Z","latest_version":6,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T13:07:48.490715Z","submitted_at":"2022-05-08T13:19:23Z","title":"CCMB: A Large-scale Chinese Cross-modal Benchmark"},"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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2205.03860."}