{"as_of":"2026-08-19T12:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8469dc8c9ec085262d7f5930e41b58b50e88b7c4bca4f5da341c10763400db0c","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":"2026-08-19T06:32:44.657259+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":"2026-08-15T18:16:15.728021Z","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":"2026-08-11T15:59:09.624289Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2405.08911","last_updated":"2024-05-14T19:06:24Z","snapshot_observed_at":"2026-08-19T06:43:00.152771Z","submitted_at":"2024-05-14T19:06:24Z","title":"CLIP with Quality Captions: A Strong Pretraining for Vision Tasks","version":1},"cited_work":{"arxiv_id":"2405.08911","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.08911","snapshot_observed_at":"2026-08-11T15:59:09.624289Z","title":"CLIP with Quality Captions: A Strong Pretraining for Vision Tasks","venue":"cs.CV","work_id":"c063f07b-5edb-46b3-b59a-af7f5c92323a","year":2024},"citing_paper":{"arxiv_id":"2412.10372","last_updated":"2024-12-13T18:59:40Z","snapshot_observed_at":"2026-08-13T21:19:28.765174Z","submitted_at":"2024-12-13T18:59:40Z","title":"UniMed-CLIP: Towards a Unified Image-Text Pretraining Paradigm for Diverse Medical Imaging Modalities","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-11T15:59:09.162066Z"},"links":{"cited_paper":"/paper/2405.08911","citing_paper":"/paper/2412.10372"},"observation_digest":"sha256:dc467b816c154c272e028894eae3d5e02413cddcb7f6d8f048d917e956c21056","observation_id":"3819070f-0637-4bdd-ad1b-d4664a7cc6b8","resolution":{"observed_at":"2026-08-11T15:59:09.632031Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.08911","last_updated":"2024-05-14T19:06:24Z","snapshot_observed_at":"2026-08-19T06:43:00.152771Z","submitted_at":"2024-05-14T19:06:24Z","title":"CLIP with Quality Captions: A Strong Pretraining for Vision Tasks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.08911","snapshot_observed_at":"2026-08-15T18:16:15.728021Z","title":"CLIP with Quality Captions: A Strong Pretraining for Vision Tasks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.18675","last_updated":"2025-07-30T20:14:41Z","snapshot_observed_at":"2026-08-19T04:26:48.812076Z","submitted_at":"2025-07-24T13:13:28Z","title":"Advancing Vision-based Human Action Recognition: Exploring Vision-Language CLIP Model for Generalisation in Domain-Independent Tasks","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T18:16:15.728021Z"},"links":{"cited_paper":"/paper/2405.08911","citing_paper":"/paper/2507.18675"},"observation_digest":"sha256:90e3dc0aa30ec26b49706045cdf4a3508ccc8211828a7c2f6d328a73eabcf13e","observation_id":"e3929c2c-f003-455f-b096-1c14574783e1","resolution":{"observed_at":"2026-08-15T18:16:15.728021Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2405.08911/citation-record","integrity":"/paper/2405.08911/integrity","json":"/paper/2405.08911/citation-record.json","paper":"/paper/2405.08911"},"outbound":[],"paper":{"arxiv_id":"2405.08911","last_updated":"2024-05-14T19:06:24Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-19T06:43:00.152771Z","submitted_at":"2024-05-14T19:06:24Z","title":"CLIP with Quality Captions: A Strong Pretraining for Vision Tasks"},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2405.08911."}