{"as_of":"2026-08-10T09:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:560663495bb1eebec9f992de7f1bbc8d13cbb97bf2066accb21756f3e0f3033d","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":"2026-08-10T06:31:04.303077+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":"2026-08-01T06:07:50.854955Z","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":"2026-05-15T20:18:15.596066Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2306.16410","last_updated":"2023-06-28T17:57:10Z","snapshot_observed_at":"2026-07-06T15:47:57.565746Z","submitted_at":"2023-06-28T17:57:10Z","title":"Towards Language Models That Can See: Computer Vision Through the LENS of Natural Language","version":1},"cited_work":{"arxiv_id":"2306.16410","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2306.16410","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2306.16410 (2023) 2","venue":null,"work_id":"a1816eeb-528f-424f-af43-2c4b3c993da8","year":2023},"citing_paper":{"arxiv_id":"2404.12390","last_updated":"2024-07-03T08:44:45Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-04-18T17:59:54Z","title":"BLINK: Multimodal Large Language Models Can See but Not Perceive","version":4},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-15T20:18:15.439163Z"},"links":{"cited_paper":"/paper/2306.16410","citing_paper":"/paper/2404.12390"},"observation_digest":"sha256:0d7653b428f89b83b51e63e56cbfb0cbb0c8bdb396cc731b0d437982a8b8cb06","observation_id":"b8bad57a-08cb-4d1f-a0c4-6a097a15bc29","resolution":{"observed_at":"2026-05-15T20:18:15.599633Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.16410","last_updated":"2023-06-28T17:57:10Z","snapshot_observed_at":"2026-07-06T15:47:57.565746Z","submitted_at":"2023-06-28T17:57:10Z","title":"Towards Language Models That Can See: Computer Vision Through the LENS of Natural Language","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.16410","snapshot_observed_at":"2026-08-01T06:07:50.854955Z","title":"arXiv preprint arXiv:2306.16410 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.22016","last_updated":"2026-07-24T06:28:57Z","snapshot_observed_at":"2026-08-05T08:00:04.839613Z","submitted_at":"2026-07-24T06:28:57Z","title":"EVL-MCoT: Enhanced Vision-Language Multi-CoT for Harmful Meme Detection","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T06:07:50.854955Z"},"links":{"cited_paper":"/paper/2306.16410","citing_paper":"/paper/2607.22016"},"observation_digest":"sha256:e0f028a63200d3af5a453903bbf2954f1fcf803c5425f948276a6f64d44c4aa9","observation_id":"9eb749c3-749c-4af5-af53-c63d26807a07","resolution":{"observed_at":"2026-08-01T06:07:50.854955Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2306.16410/citation-record","integrity":"/paper/2306.16410/integrity","json":"/paper/2306.16410/citation-record.json","paper":"/paper/2306.16410"},"outbound":[],"paper":{"arxiv_id":"2306.16410","last_updated":"2023-06-28T17:57:10Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T15:47:57.565746Z","submitted_at":"2023-06-28T17:57:10Z","title":"Towards Language Models That Can See: Computer Vision Through the LENS of Natural Language"},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2306.16410."}