{"as_of":"2026-08-11T12:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:99b018a96001ab09b9d4d2398e7f86e40c0040c325971872e52bbed80d912c4a","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":1,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":1,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T19:55:45.328993Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2205.15237","last_updated":"2022-05-30T16:52:30Z","snapshot_observed_at":"2026-07-06T13:15:32.315247Z","submitted_at":"2022-05-30T16:52:30Z","title":"VLUE: A Multi-Task Benchmark for Evaluating Vision-Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.15237","snapshot_observed_at":"2026-08-04T19:55:45.328993Z","title":"When does clip generalize better than unimodal models?arXiv preprint arXiv:2205.15237, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.09014","last_updated":"2025-09-10T21:17:32Z","snapshot_observed_at":"2026-08-11T00:31:14.002139Z","submitted_at":"2025-09-10T21:17:32Z","title":"COCO-Urdu: A Large-Scale Urdu Image-Caption Dataset with Multimodal Quality Estimation","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-04T19:55:45.328993Z"},"links":{"cited_paper":"/paper/2205.15237","citing_paper":"/paper/2509.09014"},"observation_digest":"sha256:7e84b16b609019e41040bda2a8e4f17c44e1e386215c0d64a33f91704e8b4257","observation_id":"15c4100e-016c-4368-80db-689ce493fb20","resolution":{"observed_at":"2026-08-04T19:55:45.328993Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2205.15237/citation-record","integrity":"/paper/2205.15237/integrity","json":"/paper/2205.15237/citation-record.json","paper":"/paper/2205.15237"},"outbound":[],"paper":{"arxiv_id":"2205.15237","last_updated":"2022-05-30T16:52:30Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T13:15:32.315247Z","submitted_at":"2022-05-30T16:52:30Z","title":"VLUE: A Multi-Task Benchmark for Evaluating Vision-Language Models"},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2205.15237."}