{"as_of":"2026-08-07T02:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ab66e62a10604f81b675481a1437261a5e9e7425cede7ac7c903e511f56826d1","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":"2026-08-06T06:34:29.942622+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":"2026-08-06T19:43:45.039106Z","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":"2026-08-06T19:43:51.422269Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2306.09085","last_updated":"2023-06-15T12:29:42Z","snapshot_observed_at":"2026-07-06T15:42:56.285045Z","submitted_at":"2023-06-15T12:29:42Z","title":"COSA: Concatenated Sample Pretrained Vision-Language Foundation Model","version":1},"cited_work":{"arxiv_id":"2306.09085","doi":null,"metadata_source":"pith","pith_arxiv_id":"2306.09085","snapshot_observed_at":"2026-08-06T19:43:51.422269Z","title":"COSA: Concatenated Sample Pretrained Vision-Language Foundation Model","venue":"cs.CV","work_id":"cbc9a29e-b7de-4170-b9dd-1304ca1434de","year":2023},"citing_paper":{"arxiv_id":"2507.04815","last_updated":"2025-07-07T09:33:19Z","snapshot_observed_at":"2026-08-06T19:36:27.881000Z","submitted_at":"2025-07-07T09:33:19Z","title":"From Vision To Language through Graph of Events in Space and Time: An Explainable Self-supervised Approach","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T19:43:45.039106Z"},"links":{"cited_paper":"/paper/2306.09085","citing_paper":"/paper/2507.04815"},"observation_digest":"sha256:f9b3b6eaf5ee9b2dfd598c8396f1ba467b84f5c8646b4c485495e14c9fd44752","observation_id":"91c3c52e-0afb-462d-b91c-37c160df3cce","resolution":{"observed_at":"2026-08-06T19:43:51.566919Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.09085","last_updated":"2023-06-15T12:29:42Z","snapshot_observed_at":"2026-07-06T15:42:56.285045Z","submitted_at":"2023-06-15T12:29:42Z","title":"COSA: Concatenated Sample Pretrained Vision-Language Foundation Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.09085","snapshot_observed_at":"2026-07-12T01:50:59.184754Z","title":"arXiv preprint arXiv:2306.09085 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.03530","last_updated":"2026-07-03T17:59:58Z","snapshot_observed_at":"2026-08-04T18:44:44.436706Z","submitted_at":"2026-07-03T17:59:58Z","title":"MentalThink: Shaping Thoughts in Mental SVG World","version":1},"reference_index":155,"source":"arxiv_source","source_observed_at":"2026-07-12T01:50:59.184754Z"},"links":{"cited_paper":"/paper/2306.09085","citing_paper":"/paper/2607.03530"},"observation_digest":"sha256:297d5c874d0decbef4371ebe1525c8d5c757c355bff1023a43fb899b74f6e163","observation_id":"2d5b72d0-54d9-4cbb-9673-1d8a8e4b36e0","resolution":{"observed_at":"2026-07-12T01:50:59.184754Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2306.09085/citation-record","integrity":"/paper/2306.09085/integrity","json":"/paper/2306.09085/citation-record.json","paper":"/paper/2306.09085"},"outbound":[],"paper":{"arxiv_id":"2306.09085","last_updated":"2023-06-15T12:29:42Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T15:42:56.285045Z","submitted_at":"2023-06-15T12:29:42Z","title":"COSA: Concatenated Sample Pretrained Vision-Language Foundation Model"},"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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2306.09085."}