{"as_of":"2026-08-12T17:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e90f430e81e12983dcbd7c4c38ebd36a817b152f4ec320840ac0577209fa69b2","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":"2026-08-12T06:34:41.77262+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":"2026-08-11T15:05:08.063137Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-11T15:05:08.441116Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2112.02399","last_updated":"2023-08-10T15:31:54Z","snapshot_observed_at":"2026-08-09T02:11:40.767015Z","submitted_at":"2021-12-04T18:34:24Z","title":"VT-CLIP: Enhancing Vision-Language Models with Visual-guided Texts","version":3},"cited_work":{"arxiv_id":"2112.02399","doi":null,"metadata_source":"pith","pith_arxiv_id":"2112.02399","snapshot_observed_at":"2026-08-11T15:05:08.441116Z","title":"VT-CLIP: Enhancing Vision-Language Models with Visual-guided Texts","venue":"cs.CV","work_id":"14ac142f-0562-4746-97cf-5500ab6a2658","year":2021},"citing_paper":{"arxiv_id":"2412.11375","last_updated":"2024-12-16T02:03:45Z","snapshot_observed_at":"2026-08-11T14:58:06.608662Z","submitted_at":"2024-12-16T02:03:45Z","title":"Text and Image Are Mutually Beneficial: Enhancing Training-Free Few-Shot Classification with CLIP","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-11T15:05:08.063137Z"},"links":{"cited_paper":"/paper/2112.02399","citing_paper":"/paper/2412.11375"},"observation_digest":"sha256:dae29367093e7c8ca685f5c9a2c325725ff2245cd86054375ff5cabcfd96b70e","observation_id":"448d610f-2da8-4cbb-9437-a32976bbdf97","resolution":{"observed_at":"2026-08-11T15:05:08.446152Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2112.02399/citation-record","integrity":"/paper/2112.02399/integrity","json":"/paper/2112.02399/citation-record.json","paper":"/paper/2112.02399"},"outbound":[],"paper":{"arxiv_id":"2112.02399","last_updated":"2023-08-10T15:31:54Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T02:11:40.767015Z","submitted_at":"2021-12-04T18:34:24Z","title":"VT-CLIP: Enhancing Vision-Language Models with Visual-guided Texts"},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2112.02399."}